def add(     return c "
=== RUN   TestGenerate/prompt_without_suffix
time=2024-12-25T03:23:48.023Z level=DEBUG source=gpu.go:398 msg="updating system memory data" before.total="503.7 GiB" before.free="442.0 GiB" before.free_swap="745.2 GiB" now.total="503.7 GiB" now.free="442.0 GiB" now.free_swap="745.2 GiB"
time=2024-12-25T03:23:48.023Z level=DEBUG source=sched.go:211 msg="cpu mode with first model, loading"
time=2024-12-25T03:23:48.024Z level=DEBUG source=routes.go:268 msg="generate request" images=0 prompt="def add("
=== RUN   TestGenerate/raw
time=2024-12-25T03:23:48.025Z level=DEBUG source=gpu.go:398 msg="updating system memory data" before.total="503.7 GiB" before.free="442.0 GiB" before.free_swap="745.2 GiB" now.total="503.7 GiB" now.free="442.0 GiB" now.free_swap="745.2 GiB"
time=2024-12-25T03:23:48.025Z level=DEBUG source=sched.go:211 msg="cpu mode with first model, loading"
time=2024-12-25T03:23:48.026Z level=DEBUG source=routes.go:268 msg="generate request" images=0 prompt="Help me write tests."
--- PASS: TestGenerate (0.02s)
    --- PASS: TestGenerate/missing_body (0.00s)
    --- PASS: TestGenerate/missing_model (0.00s)
    --- PASS: TestGenerate/missing_capabilities_generate (0.00s)
    --- PASS: TestGenerate/missing_capabilities_suffix (0.00s)
    --- PASS: TestGenerate/load_model (0.00s)
    --- PASS: TestGenerate/prompt (0.00s)
    --- PASS: TestGenerate/prompt_with_model_system (0.00s)
    --- PASS: TestGenerate/prompt_with_system (0.00s)
    --- PASS: TestGenerate/prompt_with_template (0.00s)
    --- PASS: TestGenerate/prompt_with_suffix (0.00s)
    --- PASS: TestGenerate/prompt_without_suffix (0.00s)
    --- PASS: TestGenerate/raw (0.00s)
=== RUN   TestList
--- PASS: TestList (0.01s)
=== RUN   Test_Routes
=== RUN   Test_Routes/Version_Handler
[GIN] 2024/12/25 - 03:23:48 | 200 |      20.591µs |       127.0.0.1 | GET      "/api/version"
=== RUN   Test_Routes/Tags_Handler_(no_tags)
[GIN] 2024/12/25 - 03:23:48 | 200 |      49.241µs |       127.0.0.1 | GET      "/api/tags"
=== RUN   Test_Routes/openai_empty_list
[GIN] 2024/12/25 - 03:23:48 | 200 |      66.922µs |       127.0.0.1 | GET      "/v1/models"
=== RUN   Test_Routes/Tags_Handler_(yes_tags)
    routes_test.go:96: Status: creating new layer sha256:a4e5e156ddec27e286f75328784d7106b60a4eb1d246e950a001a3f944fbda99
    routes_test.go:96: Status: creating new layer sha256:4f9d252f34ae677363956ffc6dd2d10918a539c5c91f5ee2fe889d9178be6ae3
    routes_test.go:96: Status: creating new layer sha256:0f239b83e9e2aad7cd997a5bb44124937a32ac1f4e98e95a2f46e7b966bfc878
    routes_test.go:96: Status: writing manifest
    routes_test.go:96: Status: success
[GIN] 2024/12/25 - 03:23:48 | 200 |     283.526µs |       127.0.0.1 | GET      "/api/tags"
=== RUN   Test_Routes/Delete_Model_Handler
    routes_test.go:96: Status: using existing layer sha256:a4e5e156ddec27e286f75328784d7106b60a4eb1d246e950a001a3f944fbda99
    routes_test.go:96: Status: using existing layer sha256:4f9d252f34ae677363956ffc6dd2d10918a539c5c91f5ee2fe889d9178be6ae3
    routes_test.go:96: Status: using existing layer sha256:0f239b83e9e2aad7cd997a5bb44124937a32ac1f4e98e95a2f46e7b966bfc878
    routes_test.go:96: Status: writing manifest
    routes_test.go:96: Status: success
[GIN] 2024/12/25 - 03:23:48 | 200 |     493.919µs |       127.0.0.1 | DELETE   "/api/delete"
=== RUN   Test_Routes/Delete_Non-existent_Model
[GIN] 2024/12/25 - 03:23:48 | 404 |      35.261µs |       127.0.0.1 | DELETE   "/api/delete"
=== RUN   Test_Routes/openai_list_models_with_tags
[GIN] 2024/12/25 - 03:23:48 | 200 |     158.033µs |       127.0.0.1 | GET      "/v1/models"
=== RUN   Test_Routes/Create_Model_Handler
[GIN] 2024/12/25 - 03:23:48 | 200 |     456.688µs |       127.0.0.1 | POST     "/api/create"
=== RUN   Test_Routes/Copy_Model_Handler
    routes_test.go:96: Status: using existing layer sha256:a4e5e156ddec27e286f75328784d7106b60a4eb1d246e950a001a3f944fbda99
    routes_test.go:96: Status: using existing layer sha256:4f9d252f34ae677363956ffc6dd2d10918a539c5c91f5ee2fe889d9178be6ae3
    routes_test.go:96: Status: using existing layer sha256:0f239b83e9e2aad7cd997a5bb44124937a32ac1f4e98e95a2f46e7b966bfc878
    routes_test.go:96: Status: writing manifest
    routes_test.go:96: Status: success
[GIN] 2024/12/25 - 03:23:48 | 200 |     429.217µs |       127.0.0.1 | POST     "/api/copy"
=== RUN   Test_Routes/Show_Model_Handler
    routes_test.go:96: Status: using existing layer sha256:a4e5e156ddec27e286f75328784d7106b60a4eb1d246e950a001a3f944fbda99
    routes_test.go:96: Status: using existing layer sha256:4f9d252f34ae677363956ffc6dd2d10918a539c5c91f5ee2fe889d9178be6ae3
    routes_test.go:96: Status: using existing layer sha256:0f239b83e9e2aad7cd997a5bb44124937a32ac1f4e98e95a2f46e7b966bfc878
    routes_test.go:96: Status: writing manifest
    routes_test.go:96: Status: success
[GIN] 2024/12/25 - 03:23:48 | 200 |     690.002µs |       127.0.0.1 | POST     "/api/show"
=== RUN   Test_Routes/openai_retrieve_model_handler
[GIN] 2024/12/25 - 03:23:48 | 200 |     234.494µs |       127.0.0.1 | GET      "/v1/models/show-model"
--- PASS: Test_Routes (0.01s)
    --- PASS: Test_Routes/Version_Handler (0.00s)
    --- PASS: Test_Routes/Tags_Handler_(no_tags) (0.00s)
    --- PASS: Test_Routes/openai_empty_list (0.00s)
    --- PASS: Test_Routes/Tags_Handler_(yes_tags) (0.00s)
    --- PASS: Test_Routes/Delete_Model_Handler (0.00s)
    --- PASS: Test_Routes/Delete_Non-existent_Model (0.00s)
    --- PASS: Test_Routes/openai_list_models_with_tags (0.00s)
    --- PASS: Test_Routes/Create_Model_Handler (0.00s)
    --- PASS: Test_Routes/Copy_Model_Handler (0.00s)
    --- PASS: Test_Routes/Show_Model_Handler (0.00s)
    --- PASS: Test_Routes/openai_retrieve_model_handler (0.00s)
=== RUN   TestManifestCaseSensitivity
    routes_test.go:571: creating
    routes_test.go:580: dir entries:
    routes_test.go:530:     d ./
    routes_test.go:530:     d ExamplE/
    routes_test.go:530:     d nAmESpace/
    routes_test.go:530:     d mODeL/
    routes_test.go:530:     - taG
    routes_test.go:582: creating (again)
    routes_test.go:588: dir entries:
    routes_test.go:530:     d ./
    routes_test.go:530:     d ExamplE/
    routes_test.go:530:     d nAmESpace/
    routes_test.go:530:     d mODeL/
    routes_test.go:530:     - taG
    routes_test.go:590: pulling
    routes_test.go:596: dir entries:
    routes_test.go:530:     d ./
    routes_test.go:530:     d ExamplE/
    routes_test.go:530:     d nAmESpace/
    routes_test.go:530:     d mODeL/
    routes_test.go:530:     - taG
    routes_test.go:598: copying
    routes_test.go:603: dir entries:
    routes_test.go:530:     d ./
    routes_test.go:530:     d ExamplE/
    routes_test.go:530:     d nAmESpace/
    routes_test.go:530:     d mODeL/
    routes_test.go:530:     - taG
--- PASS: TestManifestCaseSensitivity (0.00s)
=== RUN   TestShow
time=2024-12-25T03:23:48.043Z level=DEBUG source=gguf.go:565 msg=general.architecture type=string
time=2024-12-25T03:23:48.043Z level=DEBUG source=gguf.go:565 msg=general.architecture type=string
time=2024-12-25T03:23:48.043Z level=DEBUG source=gguf.go:565 msg=general.type type=string
--- PASS: TestShow (0.00s)
=== RUN   TestNormalize
=== RUN   TestNormalize/#00
=== RUN   TestNormalize/#01
=== RUN   TestNormalize/#02
=== RUN   TestNormalize/#03
=== RUN   TestNormalize/#04
--- PASS: TestNormalize (0.00s)
    --- PASS: TestNormalize/#00 (0.00s)
    --- PASS: TestNormalize/#01 (0.00s)
    --- PASS: TestNormalize/#02 (0.00s)
    --- PASS: TestNormalize/#03 (0.00s)
    --- PASS: TestNormalize/#04 (0.00s)
=== RUN   TestInitScheduler
--- PASS: TestInitScheduler (0.00s)
=== RUN   TestLoad
time=2024-12-25T03:23:48.044Z level=INFO source=sched.go:428 msg="NewLlamaServer failed" model=foo error="something failed to load model blah: this model may be incompatible with your version of Ollama. If you previously pulled this model, try updating it by running `ollama pull `"
time=2024-12-25T03:23:48.044Z level=INFO source=sched.go:449 msg="loaded runners" count=1
time=2024-12-25T03:23:48.044Z level=DEBUG source=sched.go:462 msg="finished setting up runner" model=foo
time=2024-12-25T03:23:48.044Z level=INFO source=sched.go:449 msg="loaded runners" count=2
time=2024-12-25T03:23:48.044Z level=ERROR source=sched.go:455 msg="error loading llama server" error="wait failure"
time=2024-12-25T03:23:48.044Z level=DEBUG source=sched.go:458 msg="triggering expiration for failed load" model=dummy_model_path
--- PASS: TestLoad (0.00s)
=== RUN   TestRequestsSameModelSameRequest
time=2024-12-25T03:23:48.045Z level=DEBUG source=gguf.go:565 msg=general.architecture type=string
time=2024-12-25T03:23:48.045Z level=DEBUG source=gguf.go:565 msg=llama.attention.head_count type=uint32
time=2024-12-25T03:23:48.045Z level=DEBUG source=sched.go:466 msg="context for request finished"
time=2024-12-25T03:23:48.045Z level=DEBUG source=gguf.go:565 msg=llama.attention.head_count_kv type=uint32
time=2024-12-25T03:23:48.045Z level=DEBUG source=gguf.go:565 msg=llama.block_count type=uint32
time=2024-12-25T03:23:48.045Z level=DEBUG source=gguf.go:565 msg=llama.context_length type=uint32
time=2024-12-25T03:23:48.045Z level=DEBUG source=gguf.go:565 msg=llama.embedding_length type=uint32
time=2024-12-25T03:23:48.045Z level=DEBUG source=gguf.go:565 msg=tokenizer.ggml.scores type=[]float32
time=2024-12-25T03:23:48.045Z level=DEBUG source=gguf.go:565 msg=tokenizer.ggml.token_type type=[]int32
time=2024-12-25T03:23:48.045Z level=DEBUG source=gguf.go:565 msg=tokenizer.ggml.tokens type=[]string
time=2024-12-25T03:23:48.045Z level=DEBUG source=gguf.go:620 msg=output.weight kind=0 shape="[1 1 1 1]" offset=0
time=2024-12-25T03:23:48.045Z level=DEBUG source=gguf.go:620 msg=blk.0.attn.weight kind=0 shape="[1 1 1 1]" offset=4
time=2024-12-25T03:23:48.045Z level=DEBUG source=gguf.go:565 msg=general.architecture type=string
time=2024-12-25T03:23:48.045Z level=DEBUG source=gguf.go:565 msg=llama.attention.head_count type=uint32
time=2024-12-25T03:23:48.045Z level=DEBUG source=gguf.go:565 msg=llama.attention.head_count_kv type=uint32
time=2024-12-25T03:23:48.045Z level=DEBUG source=gguf.go:565 msg=llama.block_count type=uint32
time=2024-12-25T03:23:48.045Z level=DEBUG source=gguf.go:565 msg=llama.context_length type=uint32
time=2024-12-25T03:23:48.046Z level=DEBUG source=gguf.go:565 msg=llama.embedding_length type=uint32
time=2024-12-25T03:23:48.046Z level=DEBUG source=gguf.go:565 msg=tokenizer.ggml.scores type=[]float32
time=2024-12-25T03:23:48.046Z level=DEBUG source=gguf.go:565 msg=tokenizer.ggml.token_type type=[]int32
time=2024-12-25T03:23:48.046Z level=DEBUG source=gguf.go:565 msg=tokenizer.ggml.tokens type=[]string
time=2024-12-25T03:23:48.046Z level=DEBUG source=gguf.go:620 msg=output.weight kind=0 shape="[1 1 1 1]" offset=0
time=2024-12-25T03:23:48.046Z level=DEBUG source=gguf.go:620 msg=blk.0.attn.weight kind=0 shape="[1 1 1 1]" offset=4
time=2024-12-25T03:23:48.046Z level=INFO source=sched_test.go:180 msg=a
time=2024-12-25T03:23:48.046Z level=DEBUG source=sched.go:105 msg="starting llm scheduler"
time=2024-12-25T03:23:48.046Z level=DEBUG source=sched.go:224 msg="loading first model" model=/usr/src/tmp/TestRequestsSameModelSameRequest792052286/001/ollama-model-11702299696
time=2024-12-25T03:23:48.046Z level=DEBUG source=memory.go:107 msg=evaluating library=metal gpu_count=1 available="[11.2 GiB]"
time=2024-12-25T03:23:48.046Z level=INFO source=sched.go:714 msg="new model will fit in available VRAM in single GPU, loading" model=/usr/src/tmp/TestRequestsSameModelSameRequest792052286/001/ollama-model-11702299696 gpu="" parallel=4 available=12000000000 required="816.0 MiB"
time=2024-12-25T03:23:48.046Z level=INFO source=sched.go:449 msg="loaded runners" count=1
time=2024-12-25T03:23:48.046Z level=DEBUG source=sched.go:462 msg="finished setting up runner" model=/usr/src/tmp/TestRequestsSameModelSameRequest792052286/001/ollama-model-11702299696
time=2024-12-25T03:23:48.046Z level=INFO source=sched_test.go:197 msg=b
time=2024-12-25T03:23:48.046Z level=DEBUG source=sched.go:575 msg="evaluating already loaded" model=/usr/src/tmp/TestRequestsSameModelSameRequest792052286/001/ollama-model-11702299696
time=2024-12-25T03:23:48.046Z level=DEBUG source=sched.go:466 msg="context for request finished"
time=2024-12-25T03:23:48.046Z level=DEBUG source=sched.go:318 msg="shutting down scheduler completed loop"
time=2024-12-25T03:23:48.046Z level=DEBUG source=sched.go:119 msg="shutting down scheduler pending loop"
time=2024-12-25T03:23:48.046Z level=DEBUG source=sched.go:407 msg="context for request finished"
--- PASS: TestRequestsSameModelSameRequest (0.00s)
=== RUN   TestRequestsSimpleReloadSameModel
time=2024-12-25T03:23:48.046Z level=DEBUG source=gguf.go:565 msg=general.architecture type=string
time=2024-12-25T03:23:48.046Z level=DEBUG source=gguf.go:565 msg=llama.attention.head_count type=uint32
time=2024-12-25T03:23:48.046Z level=DEBUG source=gguf.go:565 msg=llama.attention.head_count_kv type=uint32
time=2024-12-25T03:23:48.046Z level=DEBUG source=gguf.go:565 msg=llama.block_count type=uint32
time=2024-12-25T03:23:48.046Z level=DEBUG source=gguf.go:565 msg=llama.context_length type=uint32
time=2024-12-25T03:23:48.046Z level=DEBUG source=gguf.go:565 msg=llama.embedding_length type=uint32
time=2024-12-25T03:23:48.046Z level=DEBUG source=gguf.go:565 msg=tokenizer.ggml.scores type=[]float32
time=2024-12-25T03:23:48.046Z level=DEBUG source=gguf.go:565 msg=tokenizer.ggml.token_type type=[]int32
time=2024-12-25T03:23:48.046Z level=DEBUG source=gguf.go:565 msg=tokenizer.ggml.tokens type=[]string
time=2024-12-25T03:23:48.046Z level=DEBUG source=gguf.go:620 msg=output.weight kind=0 shape="[1 1 1 1]" offset=0
time=2024-12-25T03:23:48.046Z level=DEBUG source=gguf.go:620 msg=blk.0.attn.weight kind=0 shape="[1 1 1 1]" offset=4
time=2024-12-25T03:23:48.046Z level=DEBUG source=gguf.go:565 msg=general.architecture type=string
time=2024-12-25T03:23:48.046Z level=DEBUG source=gguf.go:565 msg=llama.attention.head_count type=uint32
time=2024-12-25T03:23:48.046Z level=DEBUG source=gguf.go:565 msg=llama.attention.head_count_kv type=uint32
time=2024-12-25T03:23:48.046Z level=DEBUG source=gguf.go:565 msg=llama.block_count type=uint32
time=2024-12-25T03:23:48.046Z level=DEBUG source=gguf.go:565 msg=llama.context_length type=uint32
time=2024-12-25T03:23:48.046Z level=DEBUG source=gguf.go:565 msg=llama.embedding_length type=uint32
time=2024-12-25T03:23:48.046Z level=DEBUG source=gguf.go:565 msg=tokenizer.ggml.scores type=[]float32
time=2024-12-25T03:23:48.046Z level=DEBUG source=gguf.go:565 msg=tokenizer.ggml.token_type type=[]int32
time=2024-12-25T03:23:48.046Z level=DEBUG source=gguf.go:565 msg=tokenizer.ggml.tokens type=[]string
time=2024-12-25T03:23:48.047Z level=DEBUG source=gguf.go:620 msg=output.weight kind=0 shape="[1 1 1 1]" offset=0
time=2024-12-25T03:23:48.047Z level=DEBUG source=gguf.go:620 msg=blk.0.attn.weight kind=0 shape="[1 1 1 1]" offset=4
time=2024-12-25T03:23:48.047Z level=INFO source=sched_test.go:224 msg=a
time=2024-12-25T03:23:48.047Z level=DEBUG source=sched.go:105 msg="starting llm scheduler"
time=2024-12-25T03:23:48.047Z level=DEBUG source=sched.go:224 msg="loading first model" model=/usr/src/tmp/TestRequestsSimpleReloadSameModel2501071799/001/ollama-model-13145843682
time=2024-12-25T03:23:48.047Z level=DEBUG source=memory.go:107 msg=evaluating library=metal gpu_count=1 available="[11.2 GiB]"
time=2024-12-25T03:23:48.047Z level=INFO source=sched.go:714 msg="new model will fit in available VRAM in single GPU, loading" model=/usr/src/tmp/TestRequestsSimpleReloadSameModel2501071799/001/ollama-model-13145843682 gpu="" parallel=4 available=12000000000 required="816.0 MiB"
time=2024-12-25T03:23:48.047Z level=INFO source=sched.go:449 msg="loaded runners" count=1
time=2024-12-25T03:23:48.047Z level=DEBUG source=sched.go:462 msg="finished setting up runner" model=/usr/src/tmp/TestRequestsSimpleReloadSameModel2501071799/001/ollama-model-13145843682
time=2024-12-25T03:23:48.047Z level=INFO source=sched_test.go:242 msg=b
time=2024-12-25T03:23:48.047Z level=DEBUG source=sched.go:575 msg="evaluating already loaded" model=/usr/src/tmp/TestRequestsSimpleReloadSameModel2501071799/001/ollama-model-13145843682
time=2024-12-25T03:23:48.047Z level=DEBUG source=sched.go:283 msg="resetting model to expire immediately to make room" modelPath=/usr/src/tmp/TestRequestsSimpleReloadSameModel2501071799/001/ollama-model-13145843682 refCount=1
time=2024-12-25T03:23:48.047Z level=DEBUG source=sched.go:296 msg="waiting for pending requests to complete and unload to occur" modelPath=/usr/src/tmp/TestRequestsSimpleReloadSameModel2501071799/001/ollama-model-13145843682
time=2024-12-25T03:23:48.048Z level=DEBUG source=sched.go:466 msg="context for request finished"
time=2024-12-25T03:23:48.048Z level=DEBUG source=sched.go:332 msg="runner with zero duration has gone idle, expiring to unload" modelPath=/usr/src/tmp/TestRequestsSimpleReloadSameModel2501071799/001/ollama-model-13145843682
time=2024-12-25T03:23:48.048Z level=DEBUG source=sched.go:357 msg="after processing request finished event" modelPath=/usr/src/tmp/TestRequestsSimpleReloadSameModel2501071799/001/ollama-model-13145843682 refCount=0
time=2024-12-25T03:23:48.048Z level=DEBUG source=sched.go:360 msg="runner expired event received" modelPath=/usr/src/tmp/TestRequestsSimpleReloadSameModel2501071799/001/ollama-model-13145843682
time=2024-12-25T03:23:48.048Z level=DEBUG source=sched.go:375 msg="got lock to unload" modelPath=/usr/src/tmp/TestRequestsSimpleReloadSameModel2501071799/001/ollama-model-13145843682
time=2024-12-25T03:23:48.048Z level=DEBUG source=sched.go:380 msg="runner released" modelPath=/usr/src/tmp/TestRequestsSimpleReloadSameModel2501071799/001/ollama-model-13145843682
time=2024-12-25T03:23:48.048Z level=DEBUG source=sched.go:384 msg="sending an unloaded event" modelPath=/usr/src/tmp/TestRequestsSimpleReloadSameModel2501071799/001/ollama-model-13145843682
time=2024-12-25T03:23:48.048Z level=DEBUG source=sched.go:302 msg="unload completed" modelPath=/usr/src/tmp/TestRequestsSimpleReloadSameModel2501071799/001/ollama-model-13145843682
time=2024-12-25T03:23:48.048Z level=DEBUG source=sched.go:224 msg="loading first model" model=/usr/src/tmp/TestRequestsSimpleReloadSameModel2501071799/001/ollama-model-13145843682
time=2024-12-25T03:23:48.048Z level=DEBUG source=memory.go:107 msg=evaluating library=metal gpu_count=1 available="[11.2 GiB]"
time=2024-12-25T03:23:48.048Z level=INFO source=sched.go:714 msg="new model will fit in available VRAM in single GPU, loading" model=/usr/src/tmp/TestRequestsSimpleReloadSameModel2501071799/001/ollama-model-13145843682 gpu="" parallel=4 available=12000000000 required="816.0 MiB"
time=2024-12-25T03:23:48.048Z level=INFO source=sched.go:449 msg="loaded runners" count=1
time=2024-12-25T03:23:48.048Z level=DEBUG source=sched.go:462 msg="finished setting up runner" model=/usr/src/tmp/TestRequestsSimpleReloadSameModel2501071799/001/ollama-model-13145843682
time=2024-12-25T03:23:48.048Z level=DEBUG source=sched.go:466 msg="context for request finished"
time=2024-12-25T03:23:48.049Z level=DEBUG source=sched.go:119 msg="shutting down scheduler pending loop"
time=2024-12-25T03:23:48.049Z level=DEBUG source=sched.go:318 msg="shutting down scheduler completed loop"
--- PASS: TestRequestsSimpleReloadSameModel (0.00s)
=== RUN   TestRequestsMultipleLoadedModels
time=2024-12-25T03:23:48.049Z level=DEBUG source=gguf.go:565 msg=general.architecture type=string
time=2024-12-25T03:23:48.049Z level=DEBUG source=gguf.go:565 msg=llama.attention.head_count type=uint32
time=2024-12-25T03:23:48.049Z level=DEBUG source=gguf.go:565 msg=llama.attention.head_count_kv type=uint32
time=2024-12-25T03:23:48.049Z level=DEBUG source=gguf.go:565 msg=llama.block_count type=uint32
time=2024-12-25T03:23:48.049Z level=DEBUG source=gguf.go:565 msg=llama.context_length type=uint32
time=2024-12-25T03:23:48.049Z level=DEBUG source=gguf.go:565 msg=llama.embedding_length type=uint32
time=2024-12-25T03:23:48.049Z level=DEBUG source=gguf.go:565 msg=tokenizer.ggml.scores type=[]float32
time=2024-12-25T03:23:48.049Z level=DEBUG source=gguf.go:565 msg=tokenizer.ggml.token_type type=[]int32
time=2024-12-25T03:23:48.049Z level=DEBUG source=gguf.go:565 msg=tokenizer.ggml.tokens type=[]string
time=2024-12-25T03:23:48.049Z level=DEBUG source=gguf.go:620 msg=output.weight kind=0 shape="[1 1 1 1]" offset=0
time=2024-12-25T03:23:48.049Z level=DEBUG source=gguf.go:620 msg=blk.0.attn.weight kind=0 shape="[1 1 1 1]" offset=4
time=2024-12-25T03:23:48.049Z level=DEBUG source=gguf.go:565 msg=general.architecture type=string
time=2024-12-25T03:23:48.049Z level=DEBUG source=gguf.go:565 msg=llama.attention.head_count type=uint32
time=2024-12-25T03:23:48.049Z level=DEBUG source=gguf.go:565 msg=llama.attention.head_count_kv type=uint32
time=2024-12-25T03:23:48.049Z level=DEBUG source=gguf.go:565 msg=llama.block_count type=uint32
time=2024-12-25T03:23:48.049Z level=DEBUG source=gguf.go:565 msg=llama.context_length type=uint32
time=2024-12-25T03:23:48.049Z level=DEBUG source=gguf.go:565 msg=llama.embedding_length type=uint32
time=2024-12-25T03:23:48.049Z level=DEBUG source=gguf.go:565 msg=tokenizer.ggml.scores type=[]float32
time=2024-12-25T03:23:48.049Z level=DEBUG source=gguf.go:565 msg=tokenizer.ggml.token_type type=[]int32
time=2024-12-25T03:23:48.049Z level=DEBUG source=gguf.go:565 msg=tokenizer.ggml.tokens type=[]string
time=2024-12-25T03:23:48.049Z level=DEBUG source=gguf.go:620 msg=output.weight kind=0 shape="[1 1 1 1]" offset=0
time=2024-12-25T03:23:48.049Z level=DEBUG source=gguf.go:620 msg=blk.0.attn.weight kind=0 shape="[1 1 1 1]" offset=4
time=2024-12-25T03:23:48.049Z level=DEBUG source=gguf.go:565 msg=general.architecture type=string
time=2024-12-25T03:23:48.049Z level=DEBUG source=gguf.go:565 msg=llama.attention.head_count type=uint32
time=2024-12-25T03:23:48.049Z level=DEBUG source=gguf.go:565 msg=llama.attention.head_count_kv type=uint32
time=2024-12-25T03:23:48.049Z level=DEBUG source=gguf.go:565 msg=llama.block_count type=uint32
time=2024-12-25T03:23:48.049Z level=DEBUG source=gguf.go:565 msg=llama.context_length type=uint32
time=2024-12-25T03:23:48.049Z level=DEBUG source=gguf.go:565 msg=llama.embedding_length type=uint32
time=2024-12-25T03:23:48.049Z level=DEBUG source=gguf.go:565 msg=tokenizer.ggml.scores type=[]float32
time=2024-12-25T03:23:48.049Z level=DEBUG source=gguf.go:565 msg=tokenizer.ggml.token_type type=[]int32
time=2024-12-25T03:23:48.049Z level=DEBUG source=gguf.go:565 msg=tokenizer.ggml.tokens type=[]string
time=2024-12-25T03:23:48.049Z level=DEBUG source=gguf.go:620 msg=output.weight kind=0 shape="[1 1 1 1]" offset=0
time=2024-12-25T03:23:48.049Z level=DEBUG source=gguf.go:620 msg=blk.0.attn.weight kind=0 shape="[1 1 1 1]" offset=4
time=2024-12-25T03:23:48.049Z level=DEBUG source=gguf.go:565 msg=general.architecture type=string
time=2024-12-25T03:23:48.049Z level=DEBUG source=gguf.go:565 msg=llama.attention.head_count type=uint32
time=2024-12-25T03:23:48.049Z level=DEBUG source=gguf.go:565 msg=llama.attention.head_count_kv type=uint32
time=2024-12-25T03:23:48.049Z level=DEBUG source=gguf.go:565 msg=llama.block_count type=uint32
time=2024-12-25T03:23:48.049Z level=DEBUG source=gguf.go:565 msg=llama.context_length type=uint32
time=2024-12-25T03:23:48.049Z level=DEBUG source=gguf.go:565 msg=llama.embedding_length type=uint32
time=2024-12-25T03:23:48.049Z level=DEBUG source=gguf.go:565 msg=tokenizer.ggml.scores type=[]float32
time=2024-12-25T03:23:48.049Z level=DEBUG source=gguf.go:565 msg=tokenizer.ggml.token_type type=[]int32
time=2024-12-25T03:23:48.049Z level=DEBUG source=gguf.go:565 msg=tokenizer.ggml.tokens type=[]string
time=2024-12-25T03:23:48.049Z level=DEBUG source=gguf.go:620 msg=output.weight kind=0 shape="[1 1 1 1]" offset=0
time=2024-12-25T03:23:48.049Z level=DEBUG source=gguf.go:620 msg=blk.0.attn.weight kind=0 shape="[1 1 1 1]" offset=4
time=2024-12-25T03:23:48.050Z level=INFO source=sched_test.go:275 msg=a
time=2024-12-25T03:23:48.050Z level=DEBUG source=sched.go:105 msg="starting llm scheduler"
time=2024-12-25T03:23:48.050Z level=DEBUG source=sched.go:224 msg="loading first model" model=/usr/src/tmp/TestRequestsMultipleLoadedModels2014467354/001/ollama-model-3a4235632858
time=2024-12-25T03:23:48.050Z level=DEBUG source=memory.go:107 msg=evaluating library=metal gpu_count=1 available="[11.2 GiB]"
time=2024-12-25T03:23:48.050Z level=INFO source=sched.go:714 msg="new model will fit in available VRAM in single GPU, loading" model=/usr/src/tmp/TestRequestsMultipleLoadedModels2014467354/001/ollama-model-3a4235632858 gpu="" parallel=4 available=12000000000 required="816.0 MiB"
time=2024-12-25T03:23:48.050Z level=INFO source=sched.go:449 msg="loaded runners" count=1
time=2024-12-25T03:23:48.050Z level=DEBUG source=sched.go:462 msg="finished setting up runner" model=/usr/src/tmp/TestRequestsMultipleLoadedModels2014467354/001/ollama-model-3a4235632858
time=2024-12-25T03:23:48.050Z level=INFO source=sched_test.go:294 msg=b
time=2024-12-25T03:23:48.050Z level=DEBUG source=sched.go:181 msg="updating default concurrency" OLLAMA_MAX_LOADED_MODELS=0x8472a0 gpu_count=1
time=2024-12-25T03:23:48.050Z level=DEBUG source=sched.go:496 msg="gpu reported" gpu="" library=metal available="11.2 GiB"
time=2024-12-25T03:23:48.050Z level=INFO source=sched.go:507 msg="updated VRAM based on existing loaded models" gpu="" library=metal total="22.4 GiB" available="11.2 GiB"
time=2024-12-25T03:23:48.050Z level=DEBUG source=memory.go:107 msg=evaluating library=metal gpu_count=1 available="[11.2 GiB]"
time=2024-12-25T03:23:48.050Z level=INFO source=sched.go:714 msg="new model will fit in available VRAM in single GPU, loading" model=/usr/src/tmp/TestRequestsMultipleLoadedModels2014467354/002/ollama-model-3b1229100209 gpu="" parallel=4 available=12000000000 required="816.0 MiB"
time=2024-12-25T03:23:48.050Z level=DEBUG source=sched.go:249 msg="new model fits with existing models, loading"
time=2024-12-25T03:23:48.050Z level=INFO source=sched.go:449 msg="loaded runners" count=2
time=2024-12-25T03:23:48.050Z level=DEBUG source=sched.go:462 msg="finished setting up runner" model=/usr/src/tmp/TestRequestsMultipleLoadedModels2014467354/002/ollama-model-3b1229100209
time=2024-12-25T03:23:48.050Z level=INFO source=sched_test.go:312 msg=c
time=2024-12-25T03:23:48.050Z level=DEBUG source=sched.go:826 msg="evaluating if CPU model load will fit in available system memory"
time=2024-12-25T03:23:48.050Z level=DEBUG source=memory.go:107 msg=evaluating library=cpu gpu_count=1 available="[24.2 GiB]"
time=2024-12-25T03:23:48.050Z level=DEBUG source=sched.go:829 msg="cpu inference mode, model fits in available system memory" model="256.0 MiB" available="24.2 GiB"
time=2024-12-25T03:23:48.050Z level=DEBUG source=sched.go:217 msg="cpu mode with available system memory or first model, loading"
time=2024-12-25T03:23:48.050Z level=INFO source=sched.go:449 msg="loaded runners" count=3
time=2024-12-25T03:23:48.050Z level=DEBUG source=sched.go:462 msg="finished setting up runner" model=/usr/src/tmp/TestRequestsMultipleLoadedModels2014467354/003/ollama-model-4a1231582389
time=2024-12-25T03:23:48.050Z level=INFO source=sched_test.go:330 msg=d
time=2024-12-25T03:23:48.050Z level=DEBUG source=sched.go:466 msg="context for request finished"
time=2024-12-25T03:23:48.050Z level=DEBUG source=sched.go:339 msg="runner with non-zero duration has gone idle, adding timer" modelPath=/usr/src/tmp/TestRequestsMultipleLoadedModels2014467354/001/ollama-model-3a4235632858 duration=5ms
time=2024-12-25T03:23:48.050Z level=DEBUG source=sched.go:357 msg="after processing request finished event" modelPath=/usr/src/tmp/TestRequestsMultipleLoadedModels2014467354/001/ollama-model-3a4235632858 refCount=0
time=2024-12-25T03:23:48.052Z level=DEBUG source=sched.go:155 msg="max runners achieved, unloading one to make room" runner_count=3
time=2024-12-25T03:23:48.052Z level=DEBUG source=sched.go:784 msg="found an idle runner to unload"
time=2024-12-25T03:23:48.052Z level=DEBUG source=sched.go:283 msg="resetting model to expire immediately to make room" modelPath=/usr/src/tmp/TestRequestsMultipleLoadedModels2014467354/001/ollama-model-3a4235632858 refCount=0
time=2024-12-25T03:23:48.052Z level=DEBUG source=sched.go:296 msg="waiting for pending requests to complete and unload to occur" modelPath=/usr/src/tmp/TestRequestsMultipleLoadedModels2014467354/001/ollama-model-3a4235632858
time=2024-12-25T03:23:48.052Z level=DEBUG source=sched.go:360 msg="runner expired event received" modelPath=/usr/src/tmp/TestRequestsMultipleLoadedModels2014467354/001/ollama-model-3a4235632858
time=2024-12-25T03:23:48.052Z level=DEBUG source=sched.go:375 msg="got lock to unload" modelPath=/usr/src/tmp/TestRequestsMultipleLoadedModels2014467354/001/ollama-model-3a4235632858
time=2024-12-25T03:23:48.052Z level=DEBUG source=sched.go:380 msg="runner released" modelPath=/usr/src/tmp/TestRequestsMultipleLoadedModels2014467354/001/ollama-model-3a4235632858
time=2024-12-25T03:23:48.052Z level=DEBUG source=sched.go:384 msg="sending an unloaded event" modelPath=/usr/src/tmp/TestRequestsMultipleLoadedModels2014467354/001/ollama-model-3a4235632858
time=2024-12-25T03:23:48.052Z level=DEBUG source=sched.go:302 msg="unload completed" modelPath=/usr/src/tmp/TestRequestsMultipleLoadedModels2014467354/001/ollama-model-3a4235632858
time=2024-12-25T03:23:48.052Z level=DEBUG source=sched.go:496 msg="gpu reported" gpu="" library=metal available="11.2 GiB"
time=2024-12-25T03:23:48.052Z level=WARN source=sched.go:499 msg="predicted usage exceeds VRAM" gpu="" totalMemory=24000000000 predicted=24000000030
time=2024-12-25T03:23:48.052Z level=INFO source=sched.go:507 msg="updated VRAM based on existing loaded models" gpu="" library=metal total="22.4 GiB" available="0 B"
time=2024-12-25T03:23:48.052Z level=DEBUG source=memory.go:107 msg=evaluating library=metal gpu_count=1 available="[0 B]"
time=2024-12-25T03:23:48.052Z level=DEBUG source=memory.go:186 msg="gpu has too little memory to allocate any layers" id="" library=metal variant="" compute="" driver=0.0 name="" total="22.4 GiB" available="0 B" minimum_memory=0 layer_size="128.0 MiB" gpu_zer_overhead="0 B" partial_offload="560.0 MiB" full_offload="560.0 MiB"
time=2024-12-25T03:23:48.052Z level=DEBUG source=memory.go:330 msg="insufficient VRAM to load any model layers"
time=2024-12-25T03:23:48.052Z level=DEBUG source=memory.go:107 msg=evaluating library=metal gpu_count=1 available="[0 B]"
time=2024-12-25T03:23:48.052Z level=DEBUG source=memory.go:186 msg="gpu has too little memory to allocate any layers" id="" library=metal variant="" compute="" driver=0.0 name="" total="22.4 GiB" available="0 B" minimum_memory=0 layer_size="32.0 MiB" gpu_zer_overhead="0 B" partial_offload="164.0 MiB" full_offload="164.0 MiB"
time=2024-12-25T03:23:48.052Z level=DEBUG source=memory.go:330 msg="insufficient VRAM to load any model layers"
time=2024-12-25T03:23:48.052Z level=DEBUG source=memory.go:107 msg=evaluating library=metal gpu_count=1 available="[0 B]"
time=2024-12-25T03:23:48.052Z level=DEBUG source=memory.go:186 msg="gpu has too little memory to allocate any layers" id="" library=metal variant="" compute="" driver=0.0 name="" total="22.4 GiB" available="0 B" minimum_memory=0 layer_size="128.0 MiB" gpu_zer_overhead="0 B" partial_offload="560.0 MiB" full_offload="560.0 MiB"
time=2024-12-25T03:23:48.053Z level=DEBUG source=memory.go:330 msg="insufficient VRAM to load any model layers"
time=2024-12-25T03:23:48.053Z level=DEBUG source=memory.go:107 msg=evaluating library=metal gpu_count=1 available="[0 B]"
time=2024-12-25T03:23:48.053Z level=DEBUG source=memory.go:186 msg="gpu has too little memory to allocate any layers" id="" library=metal variant="" compute="" driver=0.0 name="" total="22.4 GiB" available="0 B" minimum_memory=0 layer_size="32.0 MiB" gpu_zer_overhead="0 B" partial_offload="164.0 MiB" full_offload="164.0 MiB"
time=2024-12-25T03:23:48.053Z level=DEBUG source=memory.go:330 msg="insufficient VRAM to load any model layers"
time=2024-12-25T03:23:48.053Z level=DEBUG source=sched.go:789 msg="no idle runners, picking the shortest duration" count=2
time=2024-12-25T03:23:48.053Z level=DEBUG source=sched.go:283 msg="resetting model to expire immediately to make room" modelPath=/usr/src/tmp/TestRequestsMultipleLoadedModels2014467354/002/ollama-model-3b1229100209 refCount=1
time=2024-12-25T03:23:48.053Z level=DEBUG source=sched.go:296 msg="waiting for pending requests to complete and unload to occur" modelPath=/usr/src/tmp/TestRequestsMultipleLoadedModels2014467354/002/ollama-model-3b1229100209
time=2024-12-25T03:23:48.058Z level=DEBUG source=sched.go:466 msg="context for request finished"
time=2024-12-25T03:23:48.058Z level=DEBUG source=sched.go:332 msg="runner with zero duration has gone idle, expiring to unload" modelPath=/usr/src/tmp/TestRequestsMultipleLoadedModels2014467354/002/ollama-model-3b1229100209
time=2024-12-25T03:23:48.058Z level=DEBUG source=sched.go:357 msg="after processing request finished event" modelPath=/usr/src/tmp/TestRequestsMultipleLoadedModels2014467354/002/ollama-model-3b1229100209 refCount=0
time=2024-12-25T03:23:48.058Z level=DEBUG source=sched.go:360 msg="runner expired event received" modelPath=/usr/src/tmp/TestRequestsMultipleLoadedModels2014467354/002/ollama-model-3b1229100209
time=2024-12-25T03:23:48.058Z level=DEBUG source=sched.go:375 msg="got lock to unload" modelPath=/usr/src/tmp/TestRequestsMultipleLoadedModels2014467354/002/ollama-model-3b1229100209
time=2024-12-25T03:23:48.058Z level=DEBUG source=sched.go:380 msg="runner released" modelPath=/usr/src/tmp/TestRequestsMultipleLoadedModels2014467354/002/ollama-model-3b1229100209
time=2024-12-25T03:23:48.058Z level=DEBUG source=sched.go:384 msg="sending an unloaded event" modelPath=/usr/src/tmp/TestRequestsMultipleLoadedModels2014467354/002/ollama-model-3b1229100209
time=2024-12-25T03:23:48.058Z level=DEBUG source=sched.go:302 msg="unload completed" modelPath=/usr/src/tmp/TestRequestsMultipleLoadedModels2014467354/002/ollama-model-3b1229100209
time=2024-12-25T03:23:48.058Z level=DEBUG source=sched.go:496 msg="gpu reported" gpu="" library=metal available="11.2 GiB"
time=2024-12-25T03:23:48.058Z level=INFO source=sched.go:507 msg="updated VRAM based on existing loaded models" gpu="" library=metal total="22.4 GiB" available="11.2 GiB"
time=2024-12-25T03:23:48.058Z level=DEBUG source=memory.go:107 msg=evaluating library=metal gpu_count=1 available="[11.2 GiB]"
time=2024-12-25T03:23:48.058Z level=INFO source=sched.go:714 msg="new model will fit in available VRAM in single GPU, loading" model=/usr/src/tmp/TestRequestsMultipleLoadedModels2014467354/004/ollama-model-3c1449303822 gpu="" parallel=4 available=12000000000 required="816.0 MiB"
time=2024-12-25T03:23:48.058Z level=DEBUG source=sched.go:249 msg="new model fits with existing models, loading"
time=2024-12-25T03:23:48.058Z level=INFO source=sched.go:449 msg="loaded runners" count=2
time=2024-12-25T03:23:48.058Z level=DEBUG source=sched.go:462 msg="finished setting up runner" model=/usr/src/tmp/TestRequestsMultipleLoadedModels2014467354/004/ollama-model-3c1449303822
time=2024-12-25T03:23:48.058Z level=DEBUG source=sched.go:466 msg="context for request finished"
time=2024-12-25T03:23:48.058Z level=DEBUG source=sched.go:119 msg="shutting down scheduler pending loop"
time=2024-12-25T03:23:48.058Z level=DEBUG source=sched.go:318 msg="shutting down scheduler completed loop"
time=2024-12-25T03:23:48.058Z level=DEBUG source=sched.go:466 msg="context for request finished"
--- PASS: TestRequestsMultipleLoadedModels (0.01s)
=== RUN   TestGetRunner
time=2024-12-25T03:23:48.059Z level=DEBUG source=gguf.go:565 msg=general.architecture type=string
time=2024-12-25T03:23:48.059Z level=DEBUG source=gguf.go:565 msg=llama.attention.head_count type=uint32
time=2024-12-25T03:23:48.059Z level=DEBUG source=gguf.go:565 msg=llama.attention.head_count_kv type=uint32
time=2024-12-25T03:23:48.059Z level=DEBUG source=gguf.go:565 msg=llama.block_count type=uint32
time=2024-12-25T03:23:48.059Z level=DEBUG source=gguf.go:565 msg=llama.context_length type=uint32
time=2024-12-25T03:23:48.059Z level=DEBUG source=gguf.go:565 msg=llama.embedding_length type=uint32
time=2024-12-25T03:23:48.059Z level=DEBUG source=gguf.go:565 msg=tokenizer.ggml.scores type=[]float32
time=2024-12-25T03:23:48.059Z level=DEBUG source=gguf.go:565 msg=tokenizer.ggml.token_type type=[]int32
time=2024-12-25T03:23:48.059Z level=DEBUG source=gguf.go:565 msg=tokenizer.ggml.tokens type=[]string
time=2024-12-25T03:23:48.059Z level=DEBUG source=gguf.go:620 msg=output.weight kind=0 shape="[1 1 1 1]" offset=0
time=2024-12-25T03:23:48.059Z level=DEBUG source=gguf.go:620 msg=blk.0.attn.weight kind=0 shape="[1 1 1 1]" offset=4
time=2024-12-25T03:23:48.059Z level=DEBUG source=gguf.go:565 msg=general.architecture type=string
time=2024-12-25T03:23:48.059Z level=DEBUG source=gguf.go:565 msg=llama.attention.head_count type=uint32
time=2024-12-25T03:23:48.059Z level=DEBUG source=gguf.go:565 msg=llama.attention.head_count_kv type=uint32
time=2024-12-25T03:23:48.059Z level=DEBUG source=gguf.go:565 msg=llama.block_count type=uint32
time=2024-12-25T03:23:48.059Z level=DEBUG source=gguf.go:565 msg=llama.context_length type=uint32
time=2024-12-25T03:23:48.059Z level=DEBUG source=gguf.go:565 msg=llama.embedding_length type=uint32
time=2024-12-25T03:23:48.059Z level=DEBUG source=gguf.go:565 msg=tokenizer.ggml.scores type=[]float32
time=2024-12-25T03:23:48.059Z level=DEBUG source=gguf.go:565 msg=tokenizer.ggml.token_type type=[]int32
time=2024-12-25T03:23:48.059Z level=DEBUG source=gguf.go:565 msg=tokenizer.ggml.tokens type=[]string
time=2024-12-25T03:23:48.059Z level=DEBUG source=gguf.go:620 msg=output.weight kind=0 shape="[1 1 1 1]" offset=0
time=2024-12-25T03:23:48.059Z level=DEBUG source=gguf.go:620 msg=blk.0.attn.weight kind=0 shape="[1 1 1 1]" offset=4
time=2024-12-25T03:23:48.059Z level=DEBUG source=gguf.go:565 msg=general.architecture type=string
time=2024-12-25T03:23:48.059Z level=DEBUG source=gguf.go:565 msg=llama.attention.head_count type=uint32
time=2024-12-25T03:23:48.059Z level=DEBUG source=gguf.go:565 msg=llama.attention.head_count_kv type=uint32
time=2024-12-25T03:23:48.059Z level=DEBUG source=gguf.go:565 msg=llama.block_count type=uint32
time=2024-12-25T03:23:48.059Z level=DEBUG source=gguf.go:565 msg=llama.context_length type=uint32
time=2024-12-25T03:23:48.059Z level=DEBUG source=gguf.go:565 msg=llama.embedding_length type=uint32
time=2024-12-25T03:23:48.059Z level=DEBUG source=gguf.go:565 msg=tokenizer.ggml.scores type=[]float32
time=2024-12-25T03:23:48.059Z level=DEBUG source=gguf.go:565 msg=tokenizer.ggml.token_type type=[]int32
time=2024-12-25T03:23:48.059Z level=DEBUG source=gguf.go:565 msg=tokenizer.ggml.tokens type=[]string
time=2024-12-25T03:23:48.059Z level=DEBUG source=gguf.go:620 msg=output.weight kind=0 shape="[1 1 1 1]" offset=0
time=2024-12-25T03:23:48.059Z level=DEBUG source=gguf.go:620 msg=blk.0.attn.weight kind=0 shape="[1 1 1 1]" offset=4
time=2024-12-25T03:23:48.059Z level=INFO source=sched_test.go:368 msg=a
time=2024-12-25T03:23:48.059Z level=INFO source=sched_test.go:371 msg=b
time=2024-12-25T03:23:48.059Z level=DEBUG source=sched.go:105 msg="starting llm scheduler"
time=2024-12-25T03:23:48.059Z level=DEBUG source=sched.go:224 msg="loading first model" model=/usr/src/tmp/TestGetRunner1755017240/001/ollama-model-1a2082921671
time=2024-12-25T03:23:48.059Z level=DEBUG source=memory.go:107 msg=evaluating library=metal gpu_count=1 available="[11.2 GiB]"
time=2024-12-25T03:23:48.059Z level=INFO source=sched.go:714 msg="new model will fit in available VRAM in single GPU, loading" model=/usr/src/tmp/TestGetRunner1755017240/001/ollama-model-1a2082921671 gpu="" parallel=4 available=12000000000 required="816.0 MiB"
time=2024-12-25T03:23:48.059Z level=INFO source=sched.go:449 msg="loaded runners" count=1
time=2024-12-25T03:23:48.059Z level=DEBUG source=sched.go:462 msg="finished setting up runner" model=/usr/src/tmp/TestGetRunner1755017240/001/ollama-model-1a2082921671
time=2024-12-25T03:23:48.059Z level=INFO source=sched_test.go:395 msg=c
time=2024-12-25T03:23:48.059Z level=DEBUG source=sched.go:466 msg="context for request finished"
time=2024-12-25T03:23:48.059Z level=DEBUG source=sched.go:339 msg="runner with non-zero duration has gone idle, adding timer" modelPath=/usr/src/tmp/TestGetRunner1755017240/001/ollama-model-1a2082921671 duration=2ms
time=2024-12-25T03:23:48.060Z level=DEBUG source=sched.go:357 msg="after processing request finished event" modelPath=/usr/src/tmp/TestGetRunner1755017240/001/ollama-model-1a2082921671 refCount=0
time=2024-12-25T03:23:48.062Z level=DEBUG source=sched.go:341 msg="timer expired, expiring to unload" modelPath=/usr/src/tmp/TestGetRunner1755017240/001/ollama-model-1a2082921671
time=2024-12-25T03:23:48.062Z level=DEBUG source=sched.go:360 msg="runner expired event received" modelPath=/usr/src/tmp/TestGetRunner1755017240/001/ollama-model-1a2082921671
time=2024-12-25T03:23:48.062Z level=DEBUG source=sched.go:375 msg="got lock to unload" modelPath=/usr/src/tmp/TestGetRunner1755017240/001/ollama-model-1a2082921671
time=2024-12-25T03:23:48.062Z level=DEBUG source=sched.go:380 msg="runner released" modelPath=/usr/src/tmp/TestGetRunner1755017240/001/ollama-model-1a2082921671
time=2024-12-25T03:23:48.062Z level=DEBUG source=sched.go:384 msg="sending an unloaded event" modelPath=/usr/src/tmp/TestGetRunner1755017240/001/ollama-model-1a2082921671
time=2024-12-25T03:23:48.062Z level=DEBUG source=sched.go:308 msg="ignoring unload event with no pending requests"
time=2024-12-25T03:23:48.110Z level=DEBUG source=sched.go:119 msg="shutting down scheduler pending loop"
time=2024-12-25T03:23:48.110Z level=DEBUG source=sched.go:318 msg="shutting down scheduler completed loop"
--- PASS: TestGetRunner (0.05s)
=== RUN   TestExpireRunner
time=2024-12-25T03:23:48.110Z level=INFO source=sched.go:449 msg="loaded runners" count=1
time=2024-12-25T03:23:48.110Z level=DEBUG source=sched.go:462 msg="finished setting up runner" model=foo
time=2024-12-25T03:23:48.110Z level=DEBUG source=sched.go:332 msg="runner with zero duration has gone idle, expiring to unload" modelPath=foo
time=2024-12-25T03:23:48.110Z level=DEBUG source=sched.go:357 msg="after processing request finished event" modelPath=foo refCount=0
time=2024-12-25T03:23:48.110Z level=DEBUG source=sched.go:360 msg="runner expired event received" modelPath=foo
time=2024-12-25T03:23:48.110Z level=DEBUG source=sched.go:375 msg="got lock to unload" modelPath=foo
time=2024-12-25T03:23:48.110Z level=DEBUG source=sched.go:380 msg="runner released" modelPath=foo
time=2024-12-25T03:23:48.110Z level=DEBUG source=sched.go:384 msg="sending an unloaded event" modelPath=foo
time=2024-12-25T03:23:48.130Z level=DEBUG source=sched.go:466 msg="context for request finished"
time=2024-12-25T03:23:48.130Z level=DEBUG source=sched.go:318 msg="shutting down scheduler completed loop"
--- PASS: TestExpireRunner (0.02s)
=== RUN   TestPrematureExpired
time=2024-12-25T03:23:48.130Z level=DEBUG source=gguf.go:565 msg=general.architecture type=string
time=2024-12-25T03:23:48.130Z level=DEBUG source=gguf.go:565 msg=llama.attention.head_count type=uint32
time=2024-12-25T03:23:48.130Z level=DEBUG source=gguf.go:565 msg=llama.attention.head_count_kv type=uint32
time=2024-12-25T03:23:48.130Z level=DEBUG source=gguf.go:565 msg=llama.block_count type=uint32
time=2024-12-25T03:23:48.130Z level=DEBUG source=gguf.go:565 msg=llama.context_length type=uint32
time=2024-12-25T03:23:48.130Z level=DEBUG source=gguf.go:565 msg=llama.embedding_length type=uint32
time=2024-12-25T03:23:48.131Z level=DEBUG source=gguf.go:565 msg=tokenizer.ggml.scores type=[]float32
time=2024-12-25T03:23:48.131Z level=DEBUG source=gguf.go:565 msg=tokenizer.ggml.token_type type=[]int32
time=2024-12-25T03:23:48.131Z level=DEBUG source=gguf.go:565 msg=tokenizer.ggml.tokens type=[]string
time=2024-12-25T03:23:48.131Z level=DEBUG source=gguf.go:620 msg=output.weight kind=0 shape="[1 1 1 1]" offset=0
time=2024-12-25T03:23:48.131Z level=DEBUG source=gguf.go:620 msg=blk.0.attn.weight kind=0 shape="[1 1 1 1]" offset=4
time=2024-12-25T03:23:48.131Z level=DEBUG source=sched.go:105 msg="starting llm scheduler"
time=2024-12-25T03:23:48.131Z level=DEBUG source=sched.go:224 msg="loading first model" model=/usr/src/tmp/TestPrematureExpired949739262/001/ollama-model-1a2560327437
time=2024-12-25T03:23:48.131Z level=DEBUG source=memory.go:107 msg=evaluating library=metal gpu_count=1 available="[11.2 GiB]"
time=2024-12-25T03:23:48.131Z level=INFO source=sched.go:714 msg="new model will fit in available VRAM in single GPU, loading" model=/usr/src/tmp/TestPrematureExpired949739262/001/ollama-model-1a2560327437 gpu="" parallel=4 available=12000000000 required="816.0 MiB"
time=2024-12-25T03:23:48.131Z level=INFO source=sched.go:449 msg="loaded runners" count=1
time=2024-12-25T03:23:48.131Z level=DEBUG source=sched.go:462 msg="finished setting up runner" model=/usr/src/tmp/TestPrematureExpired949739262/001/ollama-model-1a2560327437
time=2024-12-25T03:23:48.131Z level=INFO source=sched_test.go:481 msg="sending premature expired event now"
time=2024-12-25T03:23:48.131Z level=DEBUG source=sched.go:360 msg="runner expired event received" modelPath=/usr/src/tmp/TestPrematureExpired949739262/001/ollama-model-1a2560327437
time=2024-12-25T03:23:48.131Z level=DEBUG source=sched.go:363 msg="expired event with positive ref count, retrying" modelPath=/usr/src/tmp/TestPrematureExpired949739262/001/ollama-model-1a2560327437 refCount=1
time=2024-12-25T03:23:48.136Z level=DEBUG source=sched.go:466 msg="context for request finished"
time=2024-12-25T03:23:48.136Z level=DEBUG source=sched.go:339 msg="runner with non-zero duration has gone idle, adding timer" modelPath=/usr/src/tmp/TestPrematureExpired949739262/001/ollama-model-1a2560327437 duration=5ms
time=2024-12-25T03:23:48.136Z level=DEBUG source=sched.go:357 msg="after processing request finished event" modelPath=/usr/src/tmp/TestPrematureExpired949739262/001/ollama-model-1a2560327437 refCount=0
time=2024-12-25T03:23:48.141Z level=DEBUG source=sched.go:360 msg="runner expired event received" modelPath=/usr/src/tmp/TestPrematureExpired949739262/001/ollama-model-1a2560327437
time=2024-12-25T03:23:48.141Z level=DEBUG source=sched.go:375 msg="got lock to unload" modelPath=/usr/src/tmp/TestPrematureExpired949739262/001/ollama-model-1a2560327437
time=2024-12-25T03:23:48.141Z level=DEBUG source=sched.go:380 msg="runner released" modelPath=/usr/src/tmp/TestPrematureExpired949739262/001/ollama-model-1a2560327437
time=2024-12-25T03:23:48.141Z level=DEBUG source=sched.go:384 msg="sending an unloaded event" modelPath=/usr/src/tmp/TestPrematureExpired949739262/001/ollama-model-1a2560327437
time=2024-12-25T03:23:48.141Z level=DEBUG source=sched.go:308 msg="ignoring unload event with no pending requests"
time=2024-12-25T03:23:48.141Z level=DEBUG source=sched.go:341 msg="timer expired, expiring to unload" modelPath=/usr/src/tmp/TestPrematureExpired949739262/001/ollama-model-1a2560327437
time=2024-12-25T03:23:48.141Z level=DEBUG source=sched.go:360 msg="runner expired event received" modelPath=/usr/src/tmp/TestPrematureExpired949739262/001/ollama-model-1a2560327437
time=2024-12-25T03:23:48.141Z level=DEBUG source=sched.go:375 msg="got lock to unload" modelPath=/usr/src/tmp/TestPrematureExpired949739262/001/ollama-model-1a2560327437
time=2024-12-25T03:23:48.141Z level=DEBUG source=sched.go:380 msg="runner released" modelPath=/usr/src/tmp/TestPrematureExpired949739262/001/ollama-model-1a2560327437
time=2024-12-25T03:23:48.141Z level=DEBUG source=sched.go:384 msg="sending an unloaded event" modelPath=/usr/src/tmp/TestPrematureExpired949739262/001/ollama-model-1a2560327437
time=2024-12-25T03:23:48.141Z level=DEBUG source=sched.go:308 msg="ignoring unload event with no pending requests"
time=2024-12-25T03:23:48.166Z level=ERROR source=sched.go:325 msg="finished request signal received after model unloaded" modelPath=/usr/src/tmp/TestPrematureExpired949739262/001/ollama-model-1a2560327437
time=2024-12-25T03:23:48.172Z level=DEBUG source=sched.go:318 msg="shutting down scheduler completed loop"
time=2024-12-25T03:23:48.172Z level=DEBUG source=sched.go:119 msg="shutting down scheduler pending loop"
--- PASS: TestPrematureExpired (0.04s)
=== RUN   TestUseLoadedRunner
time=2024-12-25T03:23:48.172Z level=DEBUG source=sched.go:407 msg="context for request finished"
--- PASS: TestUseLoadedRunner (0.00s)
=== RUN   TestUpdateFreeSpace
time=2024-12-25T03:23:48.172Z level=DEBUG source=sched.go:496 msg="gpu reported" gpu=1 library=a available="900 B"
time=2024-12-25T03:23:48.172Z level=INFO source=sched.go:507 msg="updated VRAM based on existing loaded models" gpu=1 library=a total="1000 B" available="825 B"
time=2024-12-25T03:23:48.172Z level=DEBUG source=sched.go:496 msg="gpu reported" gpu=2 library=a available="1.9 KiB"
time=2024-12-25T03:23:48.172Z level=INFO source=sched.go:507 msg="updated VRAM based on existing loaded models" gpu=2 library=a total="2.0 KiB" available="1.8 KiB"
--- PASS: TestUpdateFreeSpace (0.00s)
=== RUN   TestFilterGPUsWithoutLoadingModels
time=2024-12-25T03:23:48.172Z level=DEBUG source=sched.go:522 msg="overlapping loads detected" gpus="[{memInfo:{TotalMemory:0 FreeMemory:0 FreeSwap:0} Library:cuda Variant: MinimumMemory:0 DependencyPath:[] EnvWorkarounds:[] UnreliableFreeMemory:false ID:0 Name: Compute: DriverMajor:0 DriverMinor:0}]" model=""
time=2024-12-25T03:23:48.172Z level=DEBUG source=sched.go:522 msg="overlapping loads detected" gpus="[{memInfo:{TotalMemory:0 FreeMemory:0 FreeSwap:0} Library:cuda Variant: MinimumMemory:0 DependencyPath:[] EnvWorkarounds:[] UnreliableFreeMemory:false ID:1 Name: Compute: DriverMajor:0 DriverMinor:0}]" model=""
time=2024-12-25T03:23:48.172Z level=DEBUG source=sched.go:522 msg="overlapping loads detected" gpus=[] model=""
--- PASS: TestFilterGPUsWithoutLoadingModels (0.00s)
=== RUN   TestFindRunnerToUnload
time=2024-12-25T03:23:48.172Z level=DEBUG source=sched.go:784 msg="found an idle runner to unload"
time=2024-12-25T03:23:48.172Z level=DEBUG source=sched.go:789 msg="no idle runners, picking the shortest duration" count=2
--- PASS: TestFindRunnerToUnload (0.00s)
=== RUN   TestNeedsReload
time=2024-12-25T03:23:48.172Z level=DEBUG source=sched.go:575 msg="evaluating already loaded" model=""
time=2024-12-25T03:23:48.172Z level=DEBUG source=sched.go:575 msg="evaluating already loaded" model=""
time=2024-12-25T03:23:48.172Z level=DEBUG source=sched.go:575 msg="evaluating already loaded" model=""
time=2024-12-25T03:23:48.172Z level=DEBUG source=sched.go:575 msg="evaluating already loaded" model=""
time=2024-12-25T03:23:48.172Z level=DEBUG source=sched.go:575 msg="evaluating already loaded" model=""
time=2024-12-25T03:23:48.172Z level=DEBUG source=sched.go:575 msg="evaluating already loaded" model=""
time=2024-12-25T03:23:48.172Z level=DEBUG source=sched.go:575 msg="evaluating already loaded" model=""
--- PASS: TestNeedsReload (0.00s)
=== RUN   TestUnloadAllRunners
time=2024-12-25T03:23:48.172Z level=DEBUG source=sched.go:798 msg="shutting down runner" model=a
time=2024-12-25T03:23:48.172Z level=DEBUG source=sched.go:798 msg="shutting down runner" model=b
--- PASS: TestUnloadAllRunners (0.00s)
=== RUN   TestUnload
--- PASS: TestUnload (0.00s)
=== RUN   TestAlreadyCanceled
time=2024-12-25T03:23:48.172Z level=DEBUG source=gguf.go:565 msg=general.architecture type=string
time=2024-12-25T03:23:48.172Z level=DEBUG source=gguf.go:565 msg=llama.attention.head_count type=uint32
time=2024-12-25T03:23:48.172Z level=DEBUG source=gguf.go:565 msg=llama.attention.head_count_kv type=uint32
time=2024-12-25T03:23:48.172Z level=DEBUG source=gguf.go:565 msg=llama.block_count type=uint32
time=2024-12-25T03:23:48.172Z level=DEBUG source=gguf.go:565 msg=llama.context_length type=uint32
time=2024-12-25T03:23:48.172Z level=DEBUG source=gguf.go:565 msg=llama.embedding_length type=uint32
time=2024-12-25T03:23:48.172Z level=DEBUG source=gguf.go:565 msg=tokenizer.ggml.scores type=[]float32
time=2024-12-25T03:23:48.172Z level=DEBUG source=gguf.go:565 msg=tokenizer.ggml.token_type type=[]int32
time=2024-12-25T03:23:48.172Z level=DEBUG source=gguf.go:565 msg=tokenizer.ggml.tokens type=[]string
time=2024-12-25T03:23:48.172Z level=DEBUG source=gguf.go:620 msg=output.weight kind=0 shape="[1 1 1 1]" offset=0
time=2024-12-25T03:23:48.172Z level=DEBUG source=gguf.go:620 msg=blk.0.attn.weight kind=0 shape="[1 1 1 1]" offset=4
time=2024-12-25T03:23:48.172Z level=INFO source=sched_test.go:703 msg=scenario1a
time=2024-12-25T03:23:48.172Z level=DEBUG source=sched.go:105 msg="starting llm scheduler"
time=2024-12-25T03:23:48.172Z level=DEBUG source=sched.go:129 msg="pending request cancelled or timed out, skipping scheduling"
time=2024-12-25T03:23:48.177Z level=DEBUG source=sched.go:119 msg="shutting down scheduler pending loop"
time=2024-12-25T03:23:48.177Z level=DEBUG source=sched.go:318 msg="shutting down scheduler completed loop"
--- PASS: TestAlreadyCanceled (0.01s)
=== RUN   TestHomogeneousGPUs
time=2024-12-25T03:23:48.177Z level=DEBUG source=gguf.go:565 msg=general.architecture type=string
time=2024-12-25T03:23:48.178Z level=DEBUG source=gguf.go:565 msg=llama.attention.head_count type=uint32
time=2024-12-25T03:23:48.178Z level=DEBUG source=gguf.go:565 msg=llama.attention.head_count_kv type=uint32
time=2024-12-25T03:23:48.178Z level=DEBUG source=gguf.go:565 msg=llama.block_count type=uint32
time=2024-12-25T03:23:48.178Z level=DEBUG source=gguf.go:565 msg=llama.context_length type=uint32
time=2024-12-25T03:23:48.178Z level=DEBUG source=gguf.go:565 msg=llama.embedding_length type=uint32
time=2024-12-25T03:23:48.178Z level=DEBUG source=gguf.go:565 msg=tokenizer.ggml.scores type=[]float32
time=2024-12-25T03:23:48.178Z level=DEBUG source=gguf.go:565 msg=tokenizer.ggml.token_type type=[]int32
time=2024-12-25T03:23:48.178Z level=DEBUG source=gguf.go:565 msg=tokenizer.ggml.tokens type=[]string
time=2024-12-25T03:23:48.178Z level=DEBUG source=gguf.go:620 msg=output.weight kind=0 shape="[1 1 1 1]" offset=0
time=2024-12-25T03:23:48.178Z level=DEBUG source=gguf.go:620 msg=blk.0.attn.weight kind=0 shape="[1 1 1 1]" offset=4
time=2024-12-25T03:23:48.178Z level=INFO source=sched_test.go:736 msg=a
time=2024-12-25T03:23:48.178Z level=DEBUG source=sched.go:105 msg="starting llm scheduler"
time=2024-12-25T03:23:48.178Z level=DEBUG source=sched.go:224 msg="loading first model" model=/usr/src/tmp/TestHomogeneousGPUs3482231844/001/ollama-model-1975547269
time=2024-12-25T03:23:48.178Z level=DEBUG source=memory.go:107 msg=evaluating library=cuda gpu_count=1 available="[256.0 MiB]"
time=2024-12-25T03:23:48.178Z level=DEBUG source=memory.go:186 msg="gpu has too little memory to allocate any layers" id="" library=cuda variant="" compute="" driver=0.0 name="" total="1.0 GiB" available="256.0 MiB" minimum_memory=0 layer_size="128.0 MiB" gpu_zer_overhead="0 B" partial_offload="681.0 MiB" full_offload="560.0 MiB"
time=2024-12-25T03:23:48.178Z level=DEBUG source=memory.go:330 msg="insufficient VRAM to load any model layers"
time=2024-12-25T03:23:48.178Z level=DEBUG source=memory.go:107 msg=evaluating library=cuda gpu_count=1 available="[256.0 MiB]"
time=2024-12-25T03:23:48.178Z level=DEBUG source=memory.go:186 msg="gpu has too little memory to allocate any layers" id="" library=cuda variant="" compute="" driver=0.0 name="" total="1.0 GiB" available="256.0 MiB" minimum_memory=0 layer_size="32.0 MiB" gpu_zer_overhead="0 B" partial_offload="193.0 MiB" full_offload="164.0 MiB"
time=2024-12-25T03:23:48.178Z level=DEBUG source=memory.go:330 msg="insufficient VRAM to load any model layers"
time=2024-12-25T03:23:48.178Z level=DEBUG source=memory.go:107 msg=evaluating library=cuda gpu_count=1 available="[256.0 MiB]"
time=2024-12-25T03:23:48.178Z level=DEBUG source=memory.go:186 msg="gpu has too little memory to allocate any layers" id="" library=cuda variant="" compute="" driver=0.0 name="" total="1.0 GiB" available="256.0 MiB" minimum_memory=0 layer_size="128.0 MiB" gpu_zer_overhead="0 B" partial_offload="681.0 MiB" full_offload="560.0 MiB"
time=2024-12-25T03:23:48.178Z level=DEBUG source=memory.go:330 msg="insufficient VRAM to load any model layers"
time=2024-12-25T03:23:48.178Z level=DEBUG source=memory.go:107 msg=evaluating library=cuda gpu_count=1 available="[256.0 MiB]"
time=2024-12-25T03:23:48.178Z level=DEBUG source=memory.go:186 msg="gpu has too little memory to allocate any layers" id="" library=cuda variant="" compute="" driver=0.0 name="" total="1.0 GiB" available="256.0 MiB" minimum_memory=0 layer_size="32.0 MiB" gpu_zer_overhead="0 B" partial_offload="193.0 MiB" full_offload="164.0 MiB"
time=2024-12-25T03:23:48.178Z level=DEBUG source=memory.go:330 msg="insufficient VRAM to load any model layers"
time=2024-12-25T03:23:48.178Z level=DEBUG source=memory.go:107 msg=evaluating library=rocm gpu_count=1 available="[256.0 MiB]"
time=2024-12-25T03:23:48.178Z level=DEBUG source=memory.go:186 msg="gpu has too little memory to allocate any layers" id="" library=rocm variant="" compute="" driver=0.0 name="" total="1.0 GiB" available="256.0 MiB" minimum_memory=0 layer_size="128.0 MiB" gpu_zer_overhead="0 B" partial_offload="681.0 MiB" full_offload="560.0 MiB"
time=2024-12-25T03:23:48.178Z level=DEBUG source=memory.go:330 msg="insufficient VRAM to load any model layers"
time=2024-12-25T03:23:48.178Z level=DEBUG source=memory.go:107 msg=evaluating library=rocm gpu_count=1 available="[256.0 MiB]"
time=2024-12-25T03:23:48.178Z level=DEBUG source=memory.go:186 msg="gpu has too little memory to allocate any layers" id="" library=rocm variant="" compute="" driver=0.0 name="" total="1.0 GiB" available="256.0 MiB" minimum_memory=0 layer_size="32.0 MiB" gpu_zer_overhead="0 B" partial_offload="193.0 MiB" full_offload="164.0 MiB"
time=2024-12-25T03:23:48.178Z level=DEBUG source=memory.go:330 msg="insufficient VRAM to load any model layers"
time=2024-12-25T03:23:48.178Z level=DEBUG source=memory.go:107 msg=evaluating library=rocm gpu_count=1 available="[256.0 MiB]"
time=2024-12-25T03:23:48.178Z level=DEBUG source=memory.go:186 msg="gpu has too little memory to allocate any layers" id="" library=rocm variant="" compute="" driver=0.0 name="" total="1.0 GiB" available="256.0 MiB" minimum_memory=0 layer_size="128.0 MiB" gpu_zer_overhead="0 B" partial_offload="681.0 MiB" full_offload="560.0 MiB"
time=2024-12-25T03:23:48.178Z level=DEBUG source=memory.go:330 msg="insufficient VRAM to load any model layers"
time=2024-12-25T03:23:48.178Z level=DEBUG source=memory.go:107 msg=evaluating library=rocm gpu_count=1 available="[256.0 MiB]"
time=2024-12-25T03:23:48.178Z level=DEBUG source=memory.go:186 msg="gpu has too little memory to allocate any layers" id="" library=rocm variant="" compute="" driver=0.0 name="" total="1.0 GiB" available="256.0 MiB" minimum_memory=0 layer_size="32.0 MiB" gpu_zer_overhead="0 B" partial_offload="193.0 MiB" full_offload="164.0 MiB"
time=2024-12-25T03:23:48.178Z level=DEBUG source=memory.go:330 msg="insufficient VRAM to load any model layers"
time=2024-12-25T03:23:48.178Z level=DEBUG source=memory.go:107 msg=evaluating library=cuda gpu_count=1 available="[256.0 MiB]"
time=2024-12-25T03:23:48.178Z level=DEBUG source=memory.go:186 msg="gpu has too little memory to allocate any layers" id="" library=cuda variant="" compute="" driver=0.0 name="" total="1.0 GiB" available="256.0 MiB" minimum_memory=0 layer_size="32.0 MiB" gpu_zer_overhead="0 B" partial_offload="193.0 MiB" full_offload="164.0 MiB"
time=2024-12-25T03:23:48.178Z level=DEBUG source=memory.go:330 msg="insufficient VRAM to load any model layers"
time=2024-12-25T03:23:48.178Z level=DEBUG source=memory.go:107 msg=evaluating library=rocm gpu_count=1 available="[256.0 MiB]"
time=2024-12-25T03:23:48.178Z level=DEBUG source=memory.go:186 msg="gpu has too little memory to allocate any layers" id="" library=rocm variant="" compute="" driver=0.0 name="" total="1.0 GiB" available="256.0 MiB" minimum_memory=0 layer_size="32.0 MiB" gpu_zer_overhead="0 B" partial_offload="193.0 MiB" full_offload="164.0 MiB"
time=2024-12-25T03:23:48.178Z level=DEBUG source=memory.go:330 msg="insufficient VRAM to load any model layers"
time=2024-12-25T03:23:48.178Z level=INFO source=sched.go:449 msg="loaded runners" count=1
time=2024-12-25T03:23:48.178Z level=DEBUG source=sched.go:462 msg="finished setting up runner" model=/usr/src/tmp/TestHomogeneousGPUs3482231844/001/ollama-model-1975547269
time=2024-12-25T03:23:48.178Z level=DEBUG source=sched.go:119 msg="shutting down scheduler pending loop"
time=2024-12-25T03:23:48.178Z level=DEBUG source=sched.go:318 msg="shutting down scheduler completed loop"
--- PASS: TestHomogeneousGPUs (0.00s)
PASS
ok  	github.com/ollama/ollama/server	0.435s
=== RUN   TestAspectRatios
--- PASS: TestAspectRatios (0.00s)
=== RUN   TestGetImageSizeFitToCanvas
--- PASS: TestGetImageSizeFitToCanvas (0.00s)
=== RUN   TestGetOptimalTiledCanvas
--- PASS: TestGetOptimalTiledCanvas (0.00s)
=== RUN   TestSplitToTiles
--- PASS: TestSplitToTiles (0.00s)
=== RUN   TestResize
--- PASS: TestResize (0.16s)
=== RUN   TestPad
--- PASS: TestPad (0.01s)
=== RUN   TestPackImages
--- PASS: TestPackImages (0.11s)
=== RUN   TestPreprocess
--- PASS: TestPreprocess (0.14s)
PASS
ok  	github.com/ollama/ollama/server/imageproc	0.425s
=== RUN   TestNamed
=== RUN   TestNamed/chatml
=== RUN   TestNamed/chatml#01
=== RUN   TestNamed/zephyr
=== RUN   TestNamed/chatml#02
=== RUN   TestNamed/openchat
=== RUN   TestNamed/chatml#03
=== RUN   TestNamed/chatml#04
=== RUN   TestNamed/chatml#05
=== RUN   TestNamed/chatml#06
=== RUN   TestNamed/zephyr#01
=== RUN   TestNamed/mistral-instruct
=== RUN   TestNamed/starcoder2-instruct
=== RUN   TestNamed/llama2-chat
=== RUN   TestNamed/codellama-70b-instruct
=== RUN   TestNamed/mistral-instruct#01
=== RUN   TestNamed/chatml#07
=== RUN   TestNamed/chatml#08
=== RUN   TestNamed/chatml#09
=== RUN   TestNamed/chatml#10
=== RUN   TestNamed/alpaca
=== RUN   TestNamed/chatqa
=== RUN   TestNamed/gemma-instruct
=== RUN   TestNamed/llama3-instruct
=== RUN   TestNamed/granite-instruct
=== RUN   TestNamed/magicoder
=== RUN   TestNamed/alfred
=== RUN   TestNamed/llama2-chat#01
=== RUN   TestNamed/phi-3
=== RUN   TestNamed/phi-3#01
=== RUN   TestNamed/phi-3#02
=== RUN   TestNamed/chatqa#01
=== RUN   TestNamed/falcon-instruct
=== RUN   TestNamed/falcon-instruct#01
=== RUN   TestNamed/solar-instruct
=== RUN   TestNamed/chatml#11
--- PASS: TestNamed (0.56s)
    --- PASS: TestNamed/chatml (0.02s)
    --- PASS: TestNamed/chatml#01 (0.01s)
    --- PASS: TestNamed/zephyr (0.01s)
    --- PASS: TestNamed/chatml#02 (0.01s)
    --- PASS: TestNamed/openchat (0.01s)
    --- PASS: TestNamed/chatml#03 (0.01s)
    --- PASS: TestNamed/chatml#04 (0.01s)
    --- PASS: TestNamed/chatml#05 (0.01s)
    --- PASS: TestNamed/chatml#06 (0.01s)
    --- PASS: TestNamed/zephyr#01 (0.01s)
    --- PASS: TestNamed/mistral-instruct (0.01s)
    --- PASS: TestNamed/starcoder2-instruct (0.02s)
    --- PASS: TestNamed/llama2-chat (0.03s)
    --- PASS: TestNamed/codellama-70b-instruct (0.02s)
    --- PASS: TestNamed/mistral-instruct#01 (0.02s)
    --- PASS: TestNamed/chatml#07 (0.02s)
    --- PASS: TestNamed/chatml#08 (0.01s)
    --- PASS: TestNamed/chatml#09 (0.02s)
    --- PASS: TestNamed/chatml#10 (0.06s)
    --- PASS: TestNamed/alpaca (0.03s)
    --- PASS: TestNamed/chatqa (0.01s)
    --- PASS: TestNamed/gemma-instruct (0.02s)
    --- PASS: TestNamed/llama3-instruct (0.01s)
    --- PASS: TestNamed/granite-instruct (0.01s)
    --- PASS: TestNamed/magicoder (0.02s)
    --- PASS: TestNamed/alfred (0.02s)
    --- PASS: TestNamed/llama2-chat#01 (0.03s)
    --- PASS: TestNamed/phi-3 (0.01s)
    --- PASS: TestNamed/phi-3#01 (0.01s)
    --- PASS: TestNamed/phi-3#02 (0.01s)
    --- PASS: TestNamed/chatqa#01 (0.02s)
    --- PASS: TestNamed/falcon-instruct (0.01s)
    --- PASS: TestNamed/falcon-instruct#01 (0.01s)
    --- PASS: TestNamed/solar-instruct (0.01s)
    --- PASS: TestNamed/chatml#11 (0.01s)
=== RUN   TestTemplate
=== RUN   TestTemplate/alfred.gotmpl
=== RUN   TestTemplate/alfred.gotmpl/user
=== RUN   TestTemplate/alfred.gotmpl/legacy
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/alfred.gotmpl/user-assistant-user
=== RUN   TestTemplate/alfred.gotmpl/legacy#01
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/alfred.gotmpl/system-user-assistant-user
=== RUN   TestTemplate/alfred.gotmpl/legacy#02
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/alpaca.gotmpl
=== RUN   TestTemplate/alpaca.gotmpl/user
=== RUN   TestTemplate/alpaca.gotmpl/legacy
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/alpaca.gotmpl/user-assistant-user
=== RUN   TestTemplate/alpaca.gotmpl/legacy#01
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/alpaca.gotmpl/system-user-assistant-user
=== RUN   TestTemplate/alpaca.gotmpl/legacy#02
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/chatml.gotmpl
=== RUN   TestTemplate/chatml.gotmpl/user-assistant-user
=== RUN   TestTemplate/chatml.gotmpl/legacy
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/chatml.gotmpl/system-user-assistant-user
=== RUN   TestTemplate/chatml.gotmpl/legacy#01
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/chatml.gotmpl/user
=== RUN   TestTemplate/chatml.gotmpl/legacy#02
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/chatqa.gotmpl
=== RUN   TestTemplate/chatqa.gotmpl/user
=== RUN   TestTemplate/chatqa.gotmpl/legacy
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/chatqa.gotmpl/user-assistant-user
=== RUN   TestTemplate/chatqa.gotmpl/legacy#01
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/chatqa.gotmpl/system-user-assistant-user
=== RUN   TestTemplate/chatqa.gotmpl/legacy#02
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/codellama-70b-instruct.gotmpl
=== RUN   TestTemplate/codellama-70b-instruct.gotmpl/user
=== RUN   TestTemplate/codellama-70b-instruct.gotmpl/legacy
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/codellama-70b-instruct.gotmpl/user-assistant-user
=== RUN   TestTemplate/codellama-70b-instruct.gotmpl/legacy#01
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/codellama-70b-instruct.gotmpl/system-user-assistant-user
=== RUN   TestTemplate/codellama-70b-instruct.gotmpl/legacy#02
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/falcon-instruct.gotmpl
=== RUN   TestTemplate/falcon-instruct.gotmpl/user
=== RUN   TestTemplate/falcon-instruct.gotmpl/legacy
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/falcon-instruct.gotmpl/user-assistant-user
=== RUN   TestTemplate/falcon-instruct.gotmpl/legacy#01
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/falcon-instruct.gotmpl/system-user-assistant-user
=== RUN   TestTemplate/falcon-instruct.gotmpl/legacy#02
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/gemma-instruct.gotmpl
=== RUN   TestTemplate/gemma-instruct.gotmpl/user
=== RUN   TestTemplate/gemma-instruct.gotmpl/legacy
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/gemma-instruct.gotmpl/user-assistant-user
=== RUN   TestTemplate/gemma-instruct.gotmpl/legacy#01
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/gemma-instruct.gotmpl/system-user-assistant-user
=== RUN   TestTemplate/gemma-instruct.gotmpl/legacy#02
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/granite-instruct.gotmpl
=== RUN   TestTemplate/granite-instruct.gotmpl/user
=== RUN   TestTemplate/granite-instruct.gotmpl/legacy
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/granite-instruct.gotmpl/user-assistant-user
=== RUN   TestTemplate/granite-instruct.gotmpl/legacy#01
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/granite-instruct.gotmpl/system-user-assistant-user
=== RUN   TestTemplate/granite-instruct.gotmpl/legacy#02
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/llama2-chat.gotmpl
=== RUN   TestTemplate/llama2-chat.gotmpl/user
=== RUN   TestTemplate/llama2-chat.gotmpl/legacy
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/llama2-chat.gotmpl/user-assistant-user
=== RUN   TestTemplate/llama2-chat.gotmpl/legacy#01
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/llama2-chat.gotmpl/system-user-assistant-user
=== RUN   TestTemplate/llama2-chat.gotmpl/legacy#02
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/llama3-instruct.gotmpl
=== RUN   TestTemplate/llama3-instruct.gotmpl/user
=== RUN   TestTemplate/llama3-instruct.gotmpl/legacy
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/llama3-instruct.gotmpl/user-assistant-user
=== RUN   TestTemplate/llama3-instruct.gotmpl/legacy#01
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/llama3-instruct.gotmpl/system-user-assistant-user
=== RUN   TestTemplate/llama3-instruct.gotmpl/legacy#02
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/magicoder.gotmpl
=== RUN   TestTemplate/magicoder.gotmpl/system-user-assistant-user
=== RUN   TestTemplate/magicoder.gotmpl/legacy
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/magicoder.gotmpl/user
=== RUN   TestTemplate/magicoder.gotmpl/legacy#01
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/magicoder.gotmpl/user-assistant-user
=== RUN   TestTemplate/magicoder.gotmpl/legacy#02
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/mistral-instruct.gotmpl
=== RUN   TestTemplate/mistral-instruct.gotmpl/user
=== RUN   TestTemplate/mistral-instruct.gotmpl/legacy
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/mistral-instruct.gotmpl/user-assistant-user
=== RUN   TestTemplate/mistral-instruct.gotmpl/legacy#01
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/mistral-instruct.gotmpl/system-user-assistant-user
=== RUN   TestTemplate/mistral-instruct.gotmpl/legacy#02
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/openchat.gotmpl
=== RUN   TestTemplate/openchat.gotmpl/user
=== RUN   TestTemplate/openchat.gotmpl/legacy
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/openchat.gotmpl/user-assistant-user
=== RUN   TestTemplate/openchat.gotmpl/legacy#01
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/openchat.gotmpl/system-user-assistant-user
=== RUN   TestTemplate/openchat.gotmpl/legacy#02
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/phi-3.gotmpl
=== RUN   TestTemplate/phi-3.gotmpl/user
=== RUN   TestTemplate/phi-3.gotmpl/legacy
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/phi-3.gotmpl/user-assistant-user
=== RUN   TestTemplate/phi-3.gotmpl/legacy#01
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/phi-3.gotmpl/system-user-assistant-user
=== RUN   TestTemplate/phi-3.gotmpl/legacy#02
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/solar-instruct.gotmpl
=== RUN   TestTemplate/solar-instruct.gotmpl/user
=== RUN   TestTemplate/solar-instruct.gotmpl/legacy
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/solar-instruct.gotmpl/user-assistant-user
=== RUN   TestTemplate/solar-instruct.gotmpl/legacy#01
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/solar-instruct.gotmpl/system-user-assistant-user
=== RUN   TestTemplate/solar-instruct.gotmpl/legacy#02
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/starcoder2-instruct.gotmpl
=== RUN   TestTemplate/starcoder2-instruct.gotmpl/user
=== RUN   TestTemplate/starcoder2-instruct.gotmpl/legacy
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/starcoder2-instruct.gotmpl/user-assistant-user
=== RUN   TestTemplate/starcoder2-instruct.gotmpl/legacy#01
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/starcoder2-instruct.gotmpl/system-user-assistant-user
=== RUN   TestTemplate/starcoder2-instruct.gotmpl/legacy#02
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/vicuna.gotmpl
=== RUN   TestTemplate/vicuna.gotmpl/user
=== RUN   TestTemplate/vicuna.gotmpl/legacy
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/vicuna.gotmpl/user-assistant-user
=== RUN   TestTemplate/vicuna.gotmpl/legacy#01
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/vicuna.gotmpl/system-user-assistant-user
=== RUN   TestTemplate/vicuna.gotmpl/legacy#02
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/zephyr.gotmpl
=== RUN   TestTemplate/zephyr.gotmpl/user
=== RUN   TestTemplate/zephyr.gotmpl/legacy
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/zephyr.gotmpl/user-assistant-user
=== RUN   TestTemplate/zephyr.gotmpl/legacy#01
    template_test.go:133: legacy outputs are currently default outputs
=== RUN   TestTemplate/zephyr.gotmpl/system-user-assistant-user
=== RUN   TestTemplate/zephyr.gotmpl/legacy#02
    template_test.go:133: legacy outputs are currently default outputs
--- PASS: TestTemplate (0.01s)
    --- PASS: TestTemplate/alfred.gotmpl (0.00s)
        --- PASS: TestTemplate/alfred.gotmpl/user (0.00s)
        --- SKIP: TestTemplate/alfred.gotmpl/legacy (0.00s)
        --- PASS: TestTemplate/alfred.gotmpl/user-assistant-user (0.00s)
        --- SKIP: TestTemplate/alfred.gotmpl/legacy#01 (0.00s)
        --- PASS: TestTemplate/alfred.gotmpl/system-user-assistant-user (0.00s)
        --- SKIP: TestTemplate/alfred.gotmpl/legacy#02 (0.00s)
    --- PASS: TestTemplate/alpaca.gotmpl (0.00s)
        --- PASS: TestTemplate/alpaca.gotmpl/user (0.00s)
        --- SKIP: TestTemplate/alpaca.gotmpl/legacy (0.00s)
        --- PASS: TestTemplate/alpaca.gotmpl/user-assistant-user (0.00s)
        --- SKIP: TestTemplate/alpaca.gotmpl/legacy#01 (0.00s)
        --- PASS: TestTemplate/alpaca.gotmpl/system-user-assistant-user (0.00s)
        --- SKIP: TestTemplate/alpaca.gotmpl/legacy#02 (0.00s)
    --- PASS: TestTemplate/chatml.gotmpl (0.00s)
        --- PASS: TestTemplate/chatml.gotmpl/user-assistant-user (0.00s)
        --- SKIP: TestTemplate/chatml.gotmpl/legacy (0.00s)
        --- PASS: TestTemplate/chatml.gotmpl/system-user-assistant-user (0.00s)
        --- SKIP: TestTemplate/chatml.gotmpl/legacy#01 (0.00s)
        --- PASS: TestTemplate/chatml.gotmpl/user (0.00s)
        --- SKIP: TestTemplate/chatml.gotmpl/legacy#02 (0.00s)
    --- PASS: TestTemplate/chatqa.gotmpl (0.00s)
        --- PASS: TestTemplate/chatqa.gotmpl/user (0.00s)
        --- SKIP: TestTemplate/chatqa.gotmpl/legacy (0.00s)
        --- PASS: TestTemplate/chatqa.gotmpl/user-assistant-user (0.00s)
        --- SKIP: TestTemplate/chatqa.gotmpl/legacy#01 (0.00s)
        --- PASS: TestTemplate/chatqa.gotmpl/system-user-assistant-user (0.00s)
        --- SKIP: TestTemplate/chatqa.gotmpl/legacy#02 (0.00s)
    --- PASS: TestTemplate/codellama-70b-instruct.gotmpl (0.00s)
        --- PASS: TestTemplate/codellama-70b-instruct.gotmpl/user (0.00s)
        --- SKIP: TestTemplate/codellama-70b-instruct.gotmpl/legacy (0.00s)
        --- PASS: TestTemplate/codellama-70b-instruct.gotmpl/user-assistant-user (0.00s)
        --- SKIP: TestTemplate/codellama-70b-instruct.gotmpl/legacy#01 (0.00s)
        --- PASS: TestTemplate/codellama-70b-instruct.gotmpl/system-user-assistant-user (0.00s)
        --- SKIP: TestTemplate/codellama-70b-instruct.gotmpl/legacy#02 (0.00s)
    --- PASS: TestTemplate/falcon-instruct.gotmpl (0.00s)
        --- PASS: TestTemplate/falcon-instruct.gotmpl/user (0.00s)
        --- SKIP: TestTemplate/falcon-instruct.gotmpl/legacy (0.00s)
        --- PASS: TestTemplate/falcon-instruct.gotmpl/user-assistant-user (0.00s)
        --- SKIP: TestTemplate/falcon-instruct.gotmpl/legacy#01 (0.00s)
        --- PASS: TestTemplate/falcon-instruct.gotmpl/system-user-assistant-user (0.00s)
        --- SKIP: TestTemplate/falcon-instruct.gotmpl/legacy#02 (0.00s)
    --- PASS: TestTemplate/gemma-instruct.gotmpl (0.00s)
        --- PASS: TestTemplate/gemma-instruct.gotmpl/user (0.00s)
        --- SKIP: TestTemplate/gemma-instruct.gotmpl/legacy (0.00s)
        --- PASS: TestTemplate/gemma-instruct.gotmpl/user-assistant-user (0.00s)
        --- SKIP: TestTemplate/gemma-instruct.gotmpl/legacy#01 (0.00s)
        --- PASS: TestTemplate/gemma-instruct.gotmpl/system-user-assistant-user (0.00s)
        --- SKIP: TestTemplate/gemma-instruct.gotmpl/legacy#02 (0.00s)
    --- PASS: TestTemplate/granite-instruct.gotmpl (0.00s)
        --- PASS: TestTemplate/granite-instruct.gotmpl/user (0.00s)
        --- SKIP: TestTemplate/granite-instruct.gotmpl/legacy (0.00s)
        --- PASS: TestTemplate/granite-instruct.gotmpl/user-assistant-user (0.00s)
        --- SKIP: TestTemplate/granite-instruct.gotmpl/legacy#01 (0.00s)
        --- PASS: TestTemplate/granite-instruct.gotmpl/system-user-assistant-user (0.00s)
        --- SKIP: TestTemplate/granite-instruct.gotmpl/legacy#02 (0.00s)
    --- PASS: TestTemplate/llama2-chat.gotmpl (0.00s)
        --- PASS: TestTemplate/llama2-chat.gotmpl/user (0.00s)
        --- SKIP: TestTemplate/llama2-chat.gotmpl/legacy (0.00s)
        --- PASS: TestTemplate/llama2-chat.gotmpl/user-assistant-user (0.00s)
        --- SKIP: TestTemplate/llama2-chat.gotmpl/legacy#01 (0.00s)
        --- PASS: TestTemplate/llama2-chat.gotmpl/system-user-assistant-user (0.00s)
        --- SKIP: TestTemplate/llama2-chat.gotmpl/legacy#02 (0.00s)
    --- PASS: TestTemplate/llama3-instruct.gotmpl (0.00s)
        --- PASS: TestTemplate/llama3-instruct.gotmpl/user (0.00s)
        --- SKIP: TestTemplate/llama3-instruct.gotmpl/legacy (0.00s)
        --- PASS: TestTemplate/llama3-instruct.gotmpl/user-assistant-user (0.00s)
        --- SKIP: TestTemplate/llama3-instruct.gotmpl/legacy#01 (0.00s)
        --- PASS: TestTemplate/llama3-instruct.gotmpl/system-user-assistant-user (0.00s)
        --- SKIP: TestTemplate/llama3-instruct.gotmpl/legacy#02 (0.00s)
    --- PASS: TestTemplate/magicoder.gotmpl (0.00s)
        --- PASS: TestTemplate/magicoder.gotmpl/system-user-assistant-user (0.00s)
        --- SKIP: TestTemplate/magicoder.gotmpl/legacy (0.00s)
        --- PASS: TestTemplate/magicoder.gotmpl/user (0.00s)
        --- SKIP: TestTemplate/magicoder.gotmpl/legacy#01 (0.00s)
        --- PASS: TestTemplate/magicoder.gotmpl/user-assistant-user (0.00s)
        --- SKIP: TestTemplate/magicoder.gotmpl/legacy#02 (0.00s)
    --- PASS: TestTemplate/mistral-instruct.gotmpl (0.00s)
        --- PASS: TestTemplate/mistral-instruct.gotmpl/user (0.00s)
        --- SKIP: TestTemplate/mistral-instruct.gotmpl/legacy (0.00s)
        --- PASS: TestTemplate/mistral-instruct.gotmpl/user-assistant-user (0.00s)
        --- SKIP: TestTemplate/mistral-instruct.gotmpl/legacy#01 (0.00s)
        --- PASS: TestTemplate/mistral-instruct.gotmpl/system-user-assistant-user (0.00s)
        --- SKIP: TestTemplate/mistral-instruct.gotmpl/legacy#02 (0.00s)
    --- PASS: TestTemplate/openchat.gotmpl (0.00s)
        --- PASS: TestTemplate/openchat.gotmpl/user (0.00s)
        --- SKIP: TestTemplate/openchat.gotmpl/legacy (0.00s)
        --- PASS: TestTemplate/openchat.gotmpl/user-assistant-user (0.00s)
        --- SKIP: TestTemplate/openchat.gotmpl/legacy#01 (0.00s)
        --- PASS: TestTemplate/openchat.gotmpl/system-user-assistant-user (0.00s)
        --- SKIP: TestTemplate/openchat.gotmpl/legacy#02 (0.00s)
    --- PASS: TestTemplate/phi-3.gotmpl (0.00s)
        --- PASS: TestTemplate/phi-3.gotmpl/user (0.00s)
        --- SKIP: TestTemplate/phi-3.gotmpl/legacy (0.00s)
        --- PASS: TestTemplate/phi-3.gotmpl/user-assistant-user (0.00s)
        --- SKIP: TestTemplate/phi-3.gotmpl/legacy#01 (0.00s)
        --- PASS: TestTemplate/phi-3.gotmpl/system-user-assistant-user (0.00s)
        --- SKIP: TestTemplate/phi-3.gotmpl/legacy#02 (0.00s)
    --- PASS: TestTemplate/solar-instruct.gotmpl (0.00s)
        --- PASS: TestTemplate/solar-instruct.gotmpl/user (0.00s)
        --- SKIP: TestTemplate/solar-instruct.gotmpl/legacy (0.00s)
        --- PASS: TestTemplate/solar-instruct.gotmpl/user-assistant-user (0.00s)
        --- SKIP: TestTemplate/solar-instruct.gotmpl/legacy#01 (0.00s)
        --- PASS: TestTemplate/solar-instruct.gotmpl/system-user-assistant-user (0.00s)
        --- SKIP: TestTemplate/solar-instruct.gotmpl/legacy#02 (0.00s)
    --- PASS: TestTemplate/starcoder2-instruct.gotmpl (0.00s)
        --- PASS: TestTemplate/starcoder2-instruct.gotmpl/user (0.00s)
        --- SKIP: TestTemplate/starcoder2-instruct.gotmpl/legacy (0.00s)
        --- PASS: TestTemplate/starcoder2-instruct.gotmpl/user-assistant-user (0.00s)
        --- SKIP: TestTemplate/starcoder2-instruct.gotmpl/legacy#01 (0.00s)
        --- PASS: TestTemplate/starcoder2-instruct.gotmpl/system-user-assistant-user (0.00s)
        --- SKIP: TestTemplate/starcoder2-instruct.gotmpl/legacy#02 (0.00s)
    --- PASS: TestTemplate/vicuna.gotmpl (0.00s)
        --- PASS: TestTemplate/vicuna.gotmpl/user (0.00s)
        --- SKIP: TestTemplate/vicuna.gotmpl/legacy (0.00s)
        --- PASS: TestTemplate/vicuna.gotmpl/user-assistant-user (0.00s)
        --- SKIP: TestTemplate/vicuna.gotmpl/legacy#01 (0.00s)
        --- PASS: TestTemplate/vicuna.gotmpl/system-user-assistant-user (0.00s)
        --- SKIP: TestTemplate/vicuna.gotmpl/legacy#02 (0.00s)
    --- PASS: TestTemplate/zephyr.gotmpl (0.00s)
        --- PASS: TestTemplate/zephyr.gotmpl/user (0.00s)
        --- SKIP: TestTemplate/zephyr.gotmpl/legacy (0.00s)
        --- PASS: TestTemplate/zephyr.gotmpl/user-assistant-user (0.00s)
        --- SKIP: TestTemplate/zephyr.gotmpl/legacy#01 (0.00s)
        --- PASS: TestTemplate/zephyr.gotmpl/system-user-assistant-user (0.00s)
        --- SKIP: TestTemplate/zephyr.gotmpl/legacy#02 (0.00s)
=== RUN   TestParse
=== RUN   TestParse/#00
=== RUN   TestParse/#01
=== RUN   TestParse/#02
=== RUN   TestParse/#03
=== RUN   TestParse/#04
=== RUN   TestParse/#05
=== RUN   TestParse/#06
--- PASS: TestParse (0.00s)
    --- PASS: TestParse/#00 (0.00s)
    --- PASS: TestParse/#01 (0.00s)
    --- PASS: TestParse/#02 (0.00s)
    --- PASS: TestParse/#03 (0.00s)
    --- PASS: TestParse/#04 (0.00s)
    --- PASS: TestParse/#05 (0.00s)
    --- PASS: TestParse/#06 (0.00s)
=== RUN   TestExecuteWithMessages
=== RUN   TestExecuteWithMessages/mistral
=== RUN   TestExecuteWithMessages/mistral/no_response
=== RUN   TestExecuteWithMessages/mistral/response
=== RUN   TestExecuteWithMessages/mistral/messages
=== RUN   TestExecuteWithMessages/mistral_system
=== RUN   TestExecuteWithMessages/mistral_system/no_response
=== RUN   TestExecuteWithMessages/mistral_system/response
=== RUN   TestExecuteWithMessages/mistral_system/messages
=== RUN   TestExecuteWithMessages/mistral_assistant
=== RUN   TestExecuteWithMessages/mistral_assistant/no_response
=== RUN   TestExecuteWithMessages/mistral_assistant/response
=== RUN   TestExecuteWithMessages/mistral_assistant/messages
=== RUN   TestExecuteWithMessages/chatml
=== RUN   TestExecuteWithMessages/chatml/response
=== RUN   TestExecuteWithMessages/chatml/messages
--- PASS: TestExecuteWithMessages (0.00s)
    --- PASS: TestExecuteWithMessages/mistral (0.00s)
        --- PASS: TestExecuteWithMessages/mistral/no_response (0.00s)
        --- PASS: TestExecuteWithMessages/mistral/response (0.00s)
        --- PASS: TestExecuteWithMessages/mistral/messages (0.00s)
    --- PASS: TestExecuteWithMessages/mistral_system (0.00s)
        --- PASS: TestExecuteWithMessages/mistral_system/no_response (0.00s)
        --- PASS: TestExecuteWithMessages/mistral_system/response (0.00s)
        --- PASS: TestExecuteWithMessages/mistral_system/messages (0.00s)
    --- PASS: TestExecuteWithMessages/mistral_assistant (0.00s)
        --- PASS: TestExecuteWithMessages/mistral_assistant/no_response (0.00s)
        --- PASS: TestExecuteWithMessages/mistral_assistant/response (0.00s)
        --- PASS: TestExecuteWithMessages/mistral_assistant/messages (0.00s)
    --- PASS: TestExecuteWithMessages/chatml (0.00s)
        --- PASS: TestExecuteWithMessages/chatml/response (0.00s)
        --- PASS: TestExecuteWithMessages/chatml/messages (0.00s)
=== RUN   TestExecuteWithSuffix
=== RUN   TestExecuteWithSuffix/message
=== RUN   TestExecuteWithSuffix/prompt_suffix
--- PASS: TestExecuteWithSuffix (0.00s)
    --- PASS: TestExecuteWithSuffix/message (0.00s)
    --- PASS: TestExecuteWithSuffix/prompt_suffix (0.00s)
PASS
ok  	github.com/ollama/ollama/template	0.579s
=== RUN   TestParseNameParts
=== RUN   TestParseNameParts/registry.ollama.ai/library/dolphin-mistral:7b-v2.6-dpo-laser-q6_K
=== RUN   TestParseNameParts/scheme://host:port/namespace/model:tag
=== RUN   TestParseNameParts/host/namespace/model:tag
=== RUN   TestParseNameParts/host:port/namespace/model:tag
=== RUN   TestParseNameParts/host/namespace/model
=== RUN   TestParseNameParts/host:port/namespace/model
=== RUN   TestParseNameParts/namespace/model
=== RUN   TestParseNameParts/model
=== RUN   TestParseNameParts/h/nn/mm:t
=== RUN   TestParseNameParts/88888888888888888888888888888888888888888888888888888888888888888888888888888888/88888888888888888888888888888888888888888888888888888888888888888888888888888888/88888888888888888888888888888888888888888888888888888888888888888888888888888888:88888888888888888888888888888888888888888888888888888888888888888888888888888888
=== RUN   TestParseNameParts/33333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333/88888888888888888888888888888888888888888888888888888888888888888888888888888888/88888888888888888888888888888888888888888888888888888888888888888888888888888888:88888888888888888888888888888888888888888888888888888888888888888888888888888888
--- PASS: TestParseNameParts (0.00s)
    --- PASS: TestParseNameParts/registry.ollama.ai/library/dolphin-mistral:7b-v2.6-dpo-laser-q6_K (0.00s)
    --- PASS: TestParseNameParts/scheme://host:port/namespace/model:tag (0.00s)
    --- PASS: TestParseNameParts/host/namespace/model:tag (0.00s)
    --- PASS: TestParseNameParts/host:port/namespace/model:tag (0.00s)
    --- PASS: TestParseNameParts/host/namespace/model (0.00s)
    --- PASS: TestParseNameParts/host:port/namespace/model (0.00s)
    --- PASS: TestParseNameParts/namespace/model (0.00s)
    --- PASS: TestParseNameParts/model (0.00s)
    --- PASS: TestParseNameParts/h/nn/mm:t (0.00s)
    --- PASS: TestParseNameParts/88888888888888888888888888888888888888888888888888888888888888888888888888888888/88888888888888888888888888888888888888888888888888888888888888888888888888888888/88888888888888888888888888888888888888888888888888888888888888888888888888888888:88888888888888888888888888888888888888888888888888888888888888888888888888888888 (0.00s)
    --- PASS: TestParseNameParts/33333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333/88888888888888888888888888888888888888888888888888888888888888888888888888888888/88888888888888888888888888888888888888888888888888888888888888888888888888888888:88888888888888888888888888888888888888888888888888888888888888888888888888888888 (0.00s)
=== RUN   TestNameparseNameDefault
--- PASS: TestNameparseNameDefault (0.00s)
=== RUN   TestNameIsValid
--- PASS: TestNameIsValid (0.00s)
=== RUN   TestNameIsValidPart
=== RUN   TestNameIsValidPart/#00
=== RUN   TestNameIsValidPart/a
=== RUN   TestNameIsValidPart/a.
=== RUN   TestNameIsValidPart/a.b
=== RUN   TestNameIsValidPart/a:123
=== RUN   TestNameIsValidPart/a:123/aa/bb
=== RUN   TestNameIsValidPart/bb
=== RUN   TestNameIsValidPart/a.#01
=== RUN   TestNameIsValidPart/-h
=== RUN   TestNameIsValidPart/sha256-1000000000000000000000000000000000000000000000000000000000000000
--- PASS: TestNameIsValidPart (0.00s)
    --- PASS: TestNameIsValidPart/#00 (0.00s)
    --- PASS: TestNameIsValidPart/a (0.00s)
    --- PASS: TestNameIsValidPart/a. (0.00s)
    --- PASS: TestNameIsValidPart/a.b (0.00s)
    --- PASS: TestNameIsValidPart/a:123 (0.00s)
    --- PASS: TestNameIsValidPart/a:123/aa/bb (0.00s)
    --- PASS: TestNameIsValidPart/bb (0.00s)
    --- PASS: TestNameIsValidPart/a.#01 (0.00s)
    --- PASS: TestNameIsValidPart/-h (0.00s)
    --- PASS: TestNameIsValidPart/sha256-1000000000000000000000000000000000000000000000000000000000000000 (0.00s)
=== RUN   TestFilepathAllocs
--- PASS: TestFilepathAllocs (0.00s)
=== RUN   TestParseNameFromFilepath
=== RUN   TestParseNameFromFilepath/model
=== RUN   TestParseNameFromFilepath/host/namespace/model/tag
=== RUN   TestParseNameFromFilepath/model/tag
=== RUN   TestParseNameFromFilepath/.
=== RUN   TestParseNameFromFilepath/host:port/namespace/model/tag
=== RUN   TestParseNameFromFilepath/namespace/model/tag
=== RUN   TestParseNameFromFilepath/../../model/tag
=== RUN   TestParseNameFromFilepath/namespace/tag
=== RUN   TestParseNameFromFilepath//path/to/random/file
--- PASS: TestParseNameFromFilepath (0.00s)
    --- PASS: TestParseNameFromFilepath/model (0.00s)
    --- PASS: TestParseNameFromFilepath/host/namespace/model/tag (0.00s)
    --- PASS: TestParseNameFromFilepath/model/tag (0.00s)
    --- PASS: TestParseNameFromFilepath/. (0.00s)
    --- PASS: TestParseNameFromFilepath/host:port/namespace/model/tag (0.00s)
    --- PASS: TestParseNameFromFilepath/namespace/model/tag (0.00s)
    --- PASS: TestParseNameFromFilepath/../../model/tag (0.00s)
    --- PASS: TestParseNameFromFilepath/namespace/tag (0.00s)
    --- PASS: TestParseNameFromFilepath//path/to/random/file (0.00s)
=== RUN   TestDisplayShortest
=== RUN   TestDisplayShortest/registry.ollama.ai/library/model:latest
=== RUN   TestDisplayShortest/registry.ollama.ai/library/model:tag
=== RUN   TestDisplayShortest/registry.ollama.ai/namespace/model:tag
=== RUN   TestDisplayShortest/host/namespace/model:tag
=== RUN   TestDisplayShortest/host/library/model:tag
--- PASS: TestDisplayShortest (0.00s)
    --- PASS: TestDisplayShortest/registry.ollama.ai/library/model:latest (0.00s)
    --- PASS: TestDisplayShortest/registry.ollama.ai/library/model:tag (0.00s)
    --- PASS: TestDisplayShortest/registry.ollama.ai/namespace/model:tag (0.00s)
    --- PASS: TestDisplayShortest/host/namespace/model:tag (0.00s)
    --- PASS: TestDisplayShortest/host/library/model:tag (0.00s)
=== RUN   TestIsValidNamespace
=== RUN   TestIsValidNamespace/#00
=== RUN   TestIsValidNamespace/a
=== RUN   TestIsValidNamespace/a:b
=== RUN   TestIsValidNamespace/a/b
=== RUN   TestIsValidNamespace/a:b/c
=== RUN   TestIsValidNamespace/a/b:c
=== RUN   TestIsValidNamespace/a/b:c#01
=== RUN   TestIsValidNamespace/a/b:c/d
=== RUN   TestIsValidNamespace/a/b:c/d@e
=== RUN   TestIsValidNamespace/a/b:c/d@sha256-100
=== RUN   TestIsValidNamespace/himynameisjoe
=== RUN   TestIsValidNamespace/himynameisreallyreallyreallyreallylongbutitshouldstillbevalid
--- PASS: TestIsValidNamespace (0.00s)
    --- PASS: TestIsValidNamespace/#00 (0.00s)
    --- PASS: TestIsValidNamespace/a (0.00s)
    --- PASS: TestIsValidNamespace/a:b (0.00s)
    --- PASS: TestIsValidNamespace/a/b (0.00s)
    --- PASS: TestIsValidNamespace/a:b/c (0.00s)
    --- PASS: TestIsValidNamespace/a/b:c (0.00s)
    --- PASS: TestIsValidNamespace/a/b:c#01 (0.00s)
    --- PASS: TestIsValidNamespace/a/b:c/d (0.00s)
    --- PASS: TestIsValidNamespace/a/b:c/d@e (0.00s)
    --- PASS: TestIsValidNamespace/a/b:c/d@sha256-100 (0.00s)
    --- PASS: TestIsValidNamespace/himynameisjoe (0.00s)
    --- PASS: TestIsValidNamespace/himynameisreallyreallyreallyreallylongbutitshouldstillbevalid (0.00s)
=== RUN   FuzzName
=== RUN   FuzzName/seed#0
=== RUN   FuzzName/seed#1
=== RUN   FuzzName/seed#2
=== RUN   FuzzName/seed#3
=== RUN   FuzzName/seed#4
=== RUN   FuzzName/seed#5
=== RUN   FuzzName/seed#6
=== RUN   FuzzName/seed#7
=== RUN   FuzzName/seed#8
=== RUN   FuzzName/seed#9
=== RUN   FuzzName/seed#10
=== RUN   FuzzName/seed#11
=== RUN   FuzzName/seed#12
=== RUN   FuzzName/seed#13
=== RUN   FuzzName/seed#14
=== RUN   FuzzName/seed#15
=== RUN   FuzzName/seed#16
=== RUN   FuzzName/seed#17
=== RUN   FuzzName/seed#18
=== RUN   FuzzName/seed#19
=== RUN   FuzzName/seed#20
=== RUN   FuzzName/seed#21
=== RUN   FuzzName/seed#22
=== RUN   FuzzName/seed#23
=== RUN   FuzzName/seed#24
=== RUN   FuzzName/seed#25
=== RUN   FuzzName/seed#26
=== RUN   FuzzName/seed#27
=== RUN   FuzzName/seed#28
=== RUN   FuzzName/seed#29
=== RUN   FuzzName/d37463aa416f6bab
--- PASS: FuzzName (0.00s)
    --- PASS: FuzzName/seed#0 (0.00s)
    --- PASS: FuzzName/seed#1 (0.00s)
    --- PASS: FuzzName/seed#2 (0.00s)
    --- PASS: FuzzName/seed#3 (0.00s)
    --- PASS: FuzzName/seed#4 (0.00s)
    --- PASS: FuzzName/seed#5 (0.00s)
    --- PASS: FuzzName/seed#6 (0.00s)
    --- PASS: FuzzName/seed#7 (0.00s)
    --- PASS: FuzzName/seed#8 (0.00s)
    --- PASS: FuzzName/seed#9 (0.00s)
    --- PASS: FuzzName/seed#10 (0.00s)
    --- PASS: FuzzName/seed#11 (0.00s)
    --- PASS: FuzzName/seed#12 (0.00s)
    --- PASS: FuzzName/seed#13 (0.00s)
    --- PASS: FuzzName/seed#14 (0.00s)
    --- PASS: FuzzName/seed#15 (0.00s)
    --- PASS: FuzzName/seed#16 (0.00s)
    --- PASS: FuzzName/seed#17 (0.00s)
    --- PASS: FuzzName/seed#18 (0.00s)
    --- PASS: FuzzName/seed#19 (0.00s)
    --- PASS: FuzzName/seed#20 (0.00s)
    --- PASS: FuzzName/seed#21 (0.00s)
    --- PASS: FuzzName/seed#22 (0.00s)
    --- PASS: FuzzName/seed#23 (0.00s)
    --- PASS: FuzzName/seed#24 (0.00s)
    --- PASS: FuzzName/seed#25 (0.00s)
    --- PASS: FuzzName/seed#26 (0.00s)
    --- PASS: FuzzName/seed#27 (0.00s)
    --- PASS: FuzzName/seed#28 (0.00s)
    --- PASS: FuzzName/seed#29 (0.00s)
    --- PASS: FuzzName/d37463aa416f6bab (0.00s)
PASS
ok  	github.com/ollama/ollama/types/model	0.005s
=== RUN   TestBufferedSeeker
--- PASS: TestBufferedSeeker (0.00s)
PASS
ok  	github.com/ollama/ollama/util/bufioutil	0.002s
+ /usr/src/tmp/ollama-buildroot/usr/bin/ollama --version
+ grep -Fx 'Warning: client version is 0.5.1'
Warning: client version is 0.5.1
+ ldd /usr/src/tmp/ollama-buildroot/usr/bin/ollama
	linux-vdso.so.1 (0x00007f526eedf000)
	libstdc++.so.6 => /lib64/libstdc++.so.6 (0x00007f526c49c000)
	libm.so.6 => /lib64/libm.so.6 (0x00007f526c3ba000)
	libgcc_s.so.1 => /lib64/libgcc_s.so.1 (0x00007f526c38c000)
	libc.so.6 => /lib64/libc.so.6 (0x00007f526c1a4000)
	/lib64/ld-linux-x86-64.so.2 (0x00007f526eee1000)
+ exit 0
Processing files: ollama-0.5.1-alt1
Executing(%doc): /bin/sh -e /usr/src/tmp/rpm-tmp.97143
+ umask 022
+ /bin/mkdir -p /usr/src/RPM/BUILD
+ cd /usr/src/RPM/BUILD
+ cd ollama-0.5.1
+ DOCDIR=/usr/src/tmp/ollama-buildroot/usr/share/doc/ollama
+ export DOCDIR
+ /bin/mkdir -p /usr/src/tmp/ollama-buildroot/usr/share/doc/ollama
+ cp -prL LICENSE README.md docs examples /usr/src/tmp/ollama-buildroot/usr/share/doc/ollama
+ chmod -R go-w /usr/src/tmp/ollama-buildroot/usr/share/doc/ollama
+ chmod -R a+rX /usr/src/tmp/ollama-buildroot/usr/share/doc/ollama
+ exit 0
Finding Provides (using /usr/lib/rpm/find-provides)
Executing: /bin/sh -e /usr/src/tmp/rpm-tmp.KjmbAa
find-provides: running scripts (alternatives,debuginfo,lib,pam,perl,pkgconfig,python,python3,shell)
Finding Requires (using /usr/lib/rpm/find-requires)
Executing: /bin/sh -e /usr/src/tmp/rpm-tmp.pRogS2
find-requires: running scripts (cpp,debuginfo,files,lib,pam,perl,pkgconfig,pkgconfiglib,python,python3,rpmlib,shebang,shell,static,symlinks,systemd-services)
Finding Requires(pre) (using /usr/lib/rpm/find-scriptlet-requires)
Executing: /bin/sh -e /usr/src/tmp/rpm-tmp.xsrKf0
shell.req: /usr/src/tmp/ollama-buildroot/.pre:ollama: systemd-sysusers indexed by: /sbin/systemd-sysusers -> /sbin/systemd-sysusers, /usr/sbin/systemd-sysusers -> /usr/sbin/systemd-sysusers
shell.req: /usr/src/tmp/ollama-buildroot/.pre:ollama: systemd-sysusers -> /sbin/systemd-sysusers -> /sbin/systemd-sysusers (ambiguous, via contents_index_bin)
find-scriptlet-requires: FINDPACKAGE-COMMANDS: systemd-sysusers
Finding Requires(post) (using /usr/lib/rpm/find-scriptlet-requires)
Executing: /bin/sh -e /usr/src/tmp/rpm-tmp.amq3E8
find-scriptlet-requires: FINDPACKAGE-COMMANDS: sd_booted
Finding Requires(preun) (using /usr/lib/rpm/find-scriptlet-requires)
Executing: /bin/sh -e /usr/src/tmp/rpm-tmp.wVY4m5
find-scriptlet-requires: FINDPACKAGE-COMMANDS: sd_booted
Requires: /lib64/ld-linux-x86-64.so.2, ld-linux-x86-64.so.2()(64bit) >= set:jiids, ld-linux-x86-64.so.2(GLIBC_2.3)(64bit), libc.so.6(GLIBC_2.14)(64bit), libc.so.6(GLIBC_2.17)(64bit), libc.so.6(GLIBC_2.2.5)(64bit), libc.so.6(GLIBC_2.29)(64bit), libc.so.6(GLIBC_2.3.2)(64bit), libc.so.6(GLIBC_2.3.4)(64bit), libc.so.6(GLIBC_2.32)(64bit), libc.so.6(GLIBC_2.33)(64bit), libc.so.6(GLIBC_2.34)(64bit), libc.so.6(GLIBC_2.38)(64bit), libc.so.6(GLIBC_2.4)(64bit), libc.so.6(GLIBC_2.7)(64bit), libgcc_s.so.1(GCC_3.0)(64bit), libm.so.6(GLIBC_2.2.5)(64bit), libm.so.6(GLIBC_2.27)(64bit), libm.so.6(GLIBC_2.29)(64bit), libstdc++.so.6(CXXABI_1.3)(64bit), libstdc++.so.6(CXXABI_1.3.11)(64bit), libstdc++.so.6(CXXABI_1.3.13)(64bit), libstdc++.so.6(CXXABI_1.3.15)(64bit), libstdc++.so.6(CXXABI_1.3.2)(64bit), libstdc++.so.6(CXXABI_1.3.3)(64bit), libstdc++.so.6(CXXABI_1.3.5)(64bit), libstdc++.so.6(GLIBCXX_3.4)(64bit), libstdc++.so.6(GLIBCXX_3.4.11)(64bit), libstdc++.so.6(GLIBCXX_3.4.14)(64bit), libstdc++.so.6(GLIBCXX_3.4.15)(64bit), libstdc++.so.6(GLIBCXX_3.4.17)(64bit), libstdc++.so.6(GLIBCXX_3.4.18)(64bit), libstdc++.so.6(GLIBCXX_3.4.19)(64bit), libstdc++.so.6(GLIBCXX_3.4.20)(64bit), libstdc++.so.6(GLIBCXX_3.4.21)(64bit), libstdc++.so.6(GLIBCXX_3.4.22)(64bit), libstdc++.so.6(GLIBCXX_3.4.25)(64bit), libstdc++.so.6(GLIBCXX_3.4.26)(64bit), libstdc++.so.6(GLIBCXX_3.4.29)(64bit), libstdc++.so.6(GLIBCXX_3.4.30)(64bit), libstdc++.so.6(GLIBCXX_3.4.32)(64bit), libstdc++.so.6(GLIBCXX_3.4.9)(64bit), rtld(GNU_HASH)
Requires(interp): /bin/sh
Requires(rpmlib): rpmlib(SetVersions)
Requires(pre): /bin/sh, /sbin/systemd-sysusers
Requires(post): /bin/sh, service
Requires(preun): /bin/sh, service
Finding debuginfo files (using /usr/lib/rpm/find-debuginfo-files)
Executing: /bin/sh -e /usr/src/tmp/rpm-tmp.V0fbp1
Creating ollama-debuginfo package
Processing files: ollama-debuginfo-0.5.1-alt1
Finding Provides (using /usr/lib/rpm/find-provides)
Executing: /bin/sh -e /usr/src/tmp/rpm-tmp.TOuDyl
find-provides: running scripts (debuginfo)
Finding Requires (using /usr/lib/rpm/find-requires)
Executing: /bin/sh -e /usr/src/tmp/rpm-tmp.wBax1g
find-requires: running scripts (debuginfo)
Requires: ollama = 0.5.1-alt1, /usr/lib/debug/lib64/ld-linux-x86-64.so.2.debug, debug64(ld-linux-x86-64.so.2), debug64(libc.so.6), debug64(libgcc_s.so.1), debug64(libm.so.6), debug64(libstdc++.so.6)
Adding to ollama-debuginfo a strict dependency on ollama
Wrote: /usr/src/RPM/RPMS/x86_64/ollama-0.5.1-alt1.x86_64.rpm (w2T16.xzdio)
Wrote: /usr/src/RPM/RPMS/x86_64/ollama-debuginfo-0.5.1-alt1.x86_64.rpm (w2T16.xzdio)
898.66user 75.32system 7:52.05elapsed 206%CPU (0avgtext+0avgdata 1197612maxresident)k
0inputs+0outputs (0major+9433483minor)pagefaults 0swaps
4.12user 2.82system 8:08.12elapsed 1%CPU (0avgtext+0avgdata 131032maxresident)k
0inputs+0outputs (0major+230354minor)pagefaults 0swaps
--- ollama-0.5.1-alt1.x86_64.rpm.repo	2024-12-08 02:29:15.000000000 +0000
+++ ollama-0.5.1-alt1.x86_64.rpm.hasher	2024-12-25 03:24:01.934297425 +0000
@@ -189,3 +189,3 @@
 Provides: ollama = 0.5.1-alt1:sisyphus+364401.200.2.1
-File: /usr/bin/ollama	100755	root:root	d63c98ee5afce8aa02c33f1a537b94be	
+File: /usr/bin/ollama	100755	root:root	a93a45a5e8dd75397f9af04bf3153056	
 File: /usr/lib/systemd/system/ollama.service	100644	root:root	d5351de1e34b812d50b9b33ae3b1262f	
@@ -329,2 +329,2 @@
 File: /var/lib/ollama	40755	ollama:ollama		
-RPMIdentity: 6602b30a5b4b7b8f53bc471226d1f6911c46bca511ace3bb6655731630290c6b7ca4fb13d914141c8c4657a07f6bccf4d8f969941c28d2abaac5de708bdbb949
+RPMIdentity: 19720c845c495581251de2cfce5e7c0c2304ef339cbbb81f5c52802b54137ed9dd4b225eb4ca947cd837c8913a0f4496b316b35794637ca2fc3fe3ae023ee8db
--- ollama-debuginfo-0.5.1-alt1.x86_64.rpm.repo	2024-12-08 02:29:15.000000000 +0000
+++ ollama-debuginfo-0.5.1-alt1.x86_64.rpm.hasher	2024-12-25 03:24:02.031299125 +0000
@@ -1,4 +1,4 @@
-/usr/lib/debug/.build-id/a0	40755	root:root	
-/usr/lib/debug/.build-id/a0/fe21a9ea670c04cc2f175f2fa7b3d501ef623e	120777	root:root	../../../../bin/ollama
-/usr/lib/debug/.build-id/a0/fe21a9ea670c04cc2f175f2fa7b3d501ef623e.debug	120777	root:root	../../usr/bin/ollama.debug
+/usr/lib/debug/.build-id/5d	40755	root:root	
+/usr/lib/debug/.build-id/5d/f3b87b76149ca15fa06dec79cf46597bde19f0	120777	root:root	../../../../bin/ollama
+/usr/lib/debug/.build-id/5d/f3b87b76149ca15fa06dec79cf46597bde19f0.debug	120777	root:root	../../usr/bin/ollama.debug
 /usr/lib/debug/usr/bin/ollama.debug	100644	root:root	
@@ -1525,6 +1525,6 @@
 Provides: ollama-debuginfo = 0.5.1-alt1:sisyphus+364401.200.2.1
-File: /usr/lib/debug/.build-id/a0	40755	root:root		
-File: /usr/lib/debug/.build-id/a0/fe21a9ea670c04cc2f175f2fa7b3d501ef623e	120777	root:root		../../../../bin/ollama
-File: /usr/lib/debug/.build-id/a0/fe21a9ea670c04cc2f175f2fa7b3d501ef623e.debug	120777	root:root		../../usr/bin/ollama.debug
-File: /usr/lib/debug/usr/bin/ollama.debug	100644	root:root	ad6af65b4622c086563b26af4c9e89ec	
+File: /usr/lib/debug/.build-id/5d	40755	root:root		
+File: /usr/lib/debug/.build-id/5d/f3b87b76149ca15fa06dec79cf46597bde19f0	120777	root:root		../../../../bin/ollama
+File: /usr/lib/debug/.build-id/5d/f3b87b76149ca15fa06dec79cf46597bde19f0.debug	120777	root:root		../../usr/bin/ollama.debug
+File: /usr/lib/debug/usr/bin/ollama.debug	100644	root:root	af1fd07658459245fc9547cf593e4156	
 File: /usr/src/debug/ollama-0.5.1	40755	root:root		
@@ -3041,2 +3041,2 @@
 File: /usr/src/debug/ollama-0.5.1/version/version.go	100644	root:root	5e3e0e49d6c499f3fe40bfecff1400f8	
-RPMIdentity: 3fa01c0765d9eab5a000a6f5162fceb796f144b0a4f66c8efb5c7d1035b5c9c5a6f1ec33c8a921b07d65e8651bbad2d6baf0e792dba8c9f99d5d9c8e5a8e0743
+RPMIdentity: 0b393b1db89329615310d3a7f007cf89b3d8258f00e967bdf9610b903f08d2a94b7ae33fbe842742c525fc4f31293244bd91a222990ea1f1ff50fe8cc51d245e