2025−06−06 Diving Ollama
やっぱりunloadされて終わっているケースあるかも。。?
Just memo:
$ ollama ps NAME ID SIZE PROCESSOR UNTIL gemma3:27b-it-qat 29eb0b9aeda3 26 GB 100% GPU 1 second from now Ollama Log: [GIN] 2025/06/06 - 18:12:14 | 200 | 5m1s | 100.113.133.73 | POST "/api/chat" time=2025-06-06T18:12:14.989+09:00 level=DEBUG source=sched.go:434 msg="context for request finished" runner.name=registry.ollama.ai/library/gemma3:27b-it-qat runner.inference=rocm runner.devices=1 runner.size="24.7 GiB" runner.vram="24.7 GiB" runner.parallel=1 runner.pid=18964 runner.model="C:\\Users\\Haruki Sato\\.ollama\\models\\blobs\\sha256-ccc0cddac56136ef0969cf2e3e9ac051124c937be42503b47ec570dead85ff87" runner.num_ctx=40000 time=2025-06-06T18:12:14.989+09:00 level=DEBUG source=sched.go:343 msg="runner with non-zero duration has gone idle, adding timer" runner.name=registry.ollama.ai/library/gemma3:27b-it-qat runner.inference=rocm runner.devices=1 runner.size="24.7 GiB" runner.vram="24.7 GiB" runner.parallel=1 runner.pid=18964 runner.model="C:\\Users\\Haruki Sato\\.ollama\\models\\blobs\\sha256-ccc0cddac56136ef0969cf2e3e9ac051124c937be42503b47ec570dead85ff87" runner.num_ctx=40000 duration=5m0s time=2025-06-06T18:12:14.989+09:00 level=DEBUG source=sched.go:361 msg="after processing request finished event" runner.name=registry.ollama.ai/library/gemma3:27b-it-qat runner.inference=rocm runner.devices=1 runner.size="24.7 GiB" runner.vram="24.7 GiB" runner.parallel=1 runner.pid=18964 runner.model="C:\\Users\\Haruki Sato\\.ollama\\models\\blobs\\sha256-ccc0cddac56136ef0969cf2e3e9ac051124c937be42503b47ec570dead85ff87" runner.num_ctx=40000 refCount=0 time=2025-06-06T18:12:15.557+09:00 level=DEBUG source=ggml.go:155 msg="key not found" key=general.alignment default=32 time=2025-06-06T18:12:15.558+09:00 level=DEBUG source=sched.go:615 msg="evaluating already loaded" model="C:\\Users\\Haruki Sato\\.ollama\\models\\blobs\\sha256-ccc0cddac56136ef0969cf2e3e9ac051124c937be42503b47ec570dead85ff87" time=2025-06-06T18:12:15.564+09:00 level=DEBUG source=server.go:729 msg="completion request" images=0 prompt=13752 format="" time=2025-06-06T18:12:15.568+09:00 level=DEBUG source=vocabulary.go:52 msg="adding bos token to prompt" id=[2] time=2025-06-06T18:12:15.568+09:00 level=DEBUG source=cache.go:136 msg="loading cache slot" id=0 cache=5918 prompt=4004 used=0 remaining=4004