github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 08:30:05 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #9291] gpu VRAM usage didn't recover within timeout Error: llama runner process has terminated: error:Could not initialize Tensile host: No devices found #6059

New Issue
Closed
opened 2026-04-12 17:23:14 -05:00 by GiteaMirror · 10 comments
GiteaMirror commented 2026-04-12 17:23:14 -05:00
Owner
Copy Link

Originally created by @wangzd0209 on GitHub (Feb 22, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9291

What is the issue?

cmd ./ollama run test-qwen-0.5

when I want to run ollama i find it cannot know the device what is the problem?

PS when i run ./ollama -version the version is 0.0.0

Relevant log output

time=2025-02-22T20:51:27.157+08:00 level=DEBUG source=gpu.go:359 msg="updating system memory data" before.total="503.4 GiB" before.free="475.4 GiB" before.free_swap="15.4 GiB" now.total="503.4 GiB" now.free="475.4 GiB" now.free_swap="15.4 GiB"
time=2025-02-22T20:51:27.157+08:00 level=DEBUG source=amd_linux.go:440 msg="updating rocm free memory" gpu=5 name=1d94:6210 before="64.0 GiB" now="64.0 GiB"
time=2025-02-22T20:51:27.157+08:00 level=DEBUG source=server.go:1047 msg="stopping llama server"
time=2025-02-22T20:51:27.157+08:00 level=DEBUG source=sched.go:381 msg="runner released" modelPath=/root/.ollama/models/blobs/sha256-1b93e4b8552fa16f44b7ee8e6f94df0a0e9abe9727f45d48db9af6cab651bb5a
time=2025-02-22T20:51:27.408+08:00 level=DEBUG source=gpu.go:359 msg="updating system memory data" before.total="503.4 GiB" before.free="475.4 GiB" before.free_swap="15.4 GiB" now.total="503.4 GiB" now.free="475.4 GiB" now.free_swap="15.4 GiB"
time=2025-02-22T20:51:27.409+08:00 level=DEBUG source=amd_linux.go:440 msg="updating rocm free memory" gpu=5 name=1d94:6210 before="64.0 GiB" now="64.0 GiB"
time=2025-02-22T20:51:27.659+08:00 level=DEBUG source=gpu.go:359 msg="updating system memory data" before.total="503.4 GiB" before.free="475.4 GiB" before.free_swap="15.4 GiB" now.total="503.4 GiB" now.free="475.4 GiB" now.free_swap="15.4 GiB"
time=2025-02-22T20:51:27.659+08:00 level=DEBUG source=amd_linux.go:440 msg="updating rocm free memory" gpu=5 name=1d94:6210 before="64.0 GiB" now="64.0 GiB"
time=2025-02-22T20:51:27.909+08:00 level=DEBUG source=gpu.go:359 msg="updating system memory data" before.total="503.4 GiB" before.free="475.4 GiB" before.free_swap="15.4 GiB" now.total="503.4 GiB" now.free="475.4 GiB" now.free_swap="15.4 GiB"
time=2025-02-22T20:51:27.909+08:00 level=DEBUG source=amd_linux.go:440 msg="updating rocm free memory" gpu=5 name=1d94:6210 before="64.0 GiB" now="64.0 GiB"
time=2025-02-22T20:51:28.159+08:00 level=DEBUG source=gpu.go:359 msg="updating system memory data" before.total="503.4 GiB" before.free="475.4 GiB" before.free_swap="15.4 GiB" now.total="503.4 GiB" now.free="475.4 GiB" now.free_swap="15.4 GiB"
time=2025-02-22T20:51:28.159+08:00 level=DEBUG source=amd_linux.go:440 msg="updating rocm free memory" gpu=5 name=1d94:6210 before="64.0 GiB" now="64.0 GiB"
time=2025-02-22T20:51:28.409+08:00 level=DEBUG source=gpu.go:359 msg="updating system memory data" before.total="503.4 GiB" before.free="475.4 GiB" before.free_swap="15.4 GiB" now.total="503.4 GiB" now.free="475.4 GiB" now.free_swap="15.4 GiB"
time=2025-02-22T20:51:28.409+08:00 level=DEBUG source=amd_linux.go:440 msg="updating rocm free memory" gpu=5 name=1d94:6210 before="64.0 GiB" now="64.0 GiB"
time=2025-02-22T20:51:28.659+08:00 level=DEBUG source=gpu.go:359 msg="updating system memory data" before.total="503.4 GiB" before.free="475.4 GiB" before.free_swap="15.4 GiB" now.total="503.4 GiB" now.free="475.4 GiB" now.free_swap="15.4 GiB"
time=2025-02-22T20:51:28.659+08:00 level=DEBUG source=amd_linux.go:440 msg="updating rocm free memory" gpu=5 name=1d94:6210 before="64.0 GiB" now="64.0 GiB"
time=2025-02-22T20:51:28.909+08:00 level=DEBUG source=gpu.go:359 msg="updating system memory data" before.total="503.4 GiB" before.free="475.4 GiB" before.free_swap="15.4 GiB" now.total="503.4 GiB" now.free="475.4 GiB" now.free_swap="15.4 GiB"
time=2025-02-22T20:51:28.909+08:00 level=DEBUG source=amd_linux.go:440 msg="updating rocm free memory" gpu=5 name=1d94:6210 before="64.0 GiB" now="64.0 GiB"
time=2025-02-22T20:51:29.158+08:00 level=DEBUG source=gpu.go:359 msg="updating system memory data" before.total="503.4 GiB" before.free="475.4 GiB" before.free_swap="15.4 GiB" now.total="503.4 GiB" now.free="475.4 GiB" now.free_swap="15.4 GiB"
time=2025-02-22T20:51:29.158+08:00 level=DEBUG source=amd_linux.go:440 msg="updating rocm free memory" gpu=5 name=1d94:6210 before="64.0 GiB" now="64.0 GiB"
time=2025-02-22T20:51:29.408+08:00 level=DEBUG source=gpu.go:359 msg="updating system memory data" before.total="503.4 GiB" before.free="475.4 GiB" before.free_swap="15.4 GiB" now.total="503.4 GiB" now.free="475.4 GiB" now.free_swap="15.4 GiB"
time=2025-02-22T20:51:29.409+08:00 level=DEBUG source=amd_linux.go:440 msg="updating rocm free memory" gpu=5 name=1d94:6210 before="64.0 GiB" now="64.0 GiB"
time=2025-02-22T20:51:29.659+08:00 level=DEBUG source=gpu.go:359 msg="updating system memory data" before.total="503.4 GiB" before.free="475.4 GiB" before.free_swap="15.4 GiB" now.total="503.4 GiB" now.free="475.4 GiB" now.free_swap="15.4 GiB"
time=2025-02-22T20:51:29.659+08:00 level=DEBUG source=amd_linux.go:440 msg="updating rocm free memory" gpu=5 name=1d94:6210 before="64.0 GiB" now="64.0 GiB"
time=2025-02-22T20:51:29.909+08:00 level=DEBUG source=gpu.go:359 msg="updating system memory data" before.total="503.4 GiB" before.free="475.4 GiB" before.free_swap="15.4 GiB" now.total="503.4 GiB" now.free="475.4 GiB" now.free_swap="15.4 GiB"
time=2025-02-22T20:51:29.909+08:00 level=DEBUG source=amd_linux.go:440 msg="updating rocm free memory" gpu=5 name=1d94:6210 before="64.0 GiB" now="64.0 GiB"
time=2025-02-22T20:51:30.159+08:00 level=DEBUG source=gpu.go:359 msg="updating system memory data" before.total="503.4 GiB" before.free="475.4 GiB" before.free_swap="15.4 GiB" now.total="503.4 GiB" now.free="475.4 GiB" now.free_swap="15.4 GiB"
time=2025-02-22T20:51:30.159+08:00 level=DEBUG source=amd_linux.go:440 msg="updating rocm free memory" gpu=5 name=1d94:6210 before="64.0 GiB" now="64.0 GiB"
time=2025-02-22T20:51:30.408+08:00 level=DEBUG source=gpu.go:359 msg="updating system memory data" before.total="503.4 GiB" before.free="475.4 GiB" before.free_swap="15.4 GiB" now.total="503.4 GiB" now.free="475.4 GiB" now.free_swap="15.4 GiB"
time=2025-02-22T20:51:30.408+08:00 level=DEBUG source=amd_linux.go:440 msg="updating rocm free memory" gpu=5 name=1d94:6210 before="64.0 GiB" now="64.0 GiB"
time=2025-02-22T20:51:30.658+08:00 level=DEBUG source=gpu.go:359 msg="updating system memory data" before.total="503.4 GiB" before.free="475.4 GiB" before.free_swap="15.4 GiB" now.total="503.4 GiB" now.free="475.4 GiB" now.free_swap="15.4 GiB"
time=2025-02-22T20:51:30.658+08:00 level=DEBUG source=amd_linux.go:440 msg="updating rocm free memory" gpu=5 name=1d94:6210 before="64.0 GiB" now="64.0 GiB"
time=2025-02-22T20:51:30.908+08:00 level=DEBUG source=gpu.go:359 msg="updating system memory data" before.total="503.4 GiB" before.free="475.4 GiB" before.free_swap="15.4 GiB" now.total="503.4 GiB" now.free="475.4 GiB" now.free_swap="15.4 GiB"
time=2025-02-22T20:51:30.908+08:00 level=DEBUG source=amd_linux.go:440 msg="updating rocm free memory" gpu=5 name=1d94:6210 before="64.0 GiB" now="64.0 GiB"
time=2025-02-22T20:51:31.158+08:00 level=DEBUG source=gpu.go:359 msg="updating system memory data" before.total="503.4 GiB" before.free="475.4 GiB" before.free_swap="15.4 GiB" now.total="503.4 GiB" now.free="475.4 GiB" now.free_swap="15.4 GiB"
time=2025-02-22T20:51:31.158+08:00 level=DEBUG source=amd_linux.go:440 msg="updating rocm free memory" gpu=5 name=1d94:6210 before="64.0 GiB" now="64.0 GiB"
time=2025-02-22T20:51:31.408+08:00 level=DEBUG source=gpu.go:359 msg="updating system memory data" before.total="503.4 GiB" before.free="475.4 GiB" before.free_swap="15.4 GiB" now.total="503.4 GiB" now.free="475.4 GiB" now.free_swap="15.4 GiB"
time=2025-02-22T20:51:31.408+08:00 level=DEBUG source=amd_linux.go:440 msg="updating rocm free memory" gpu=5 name=1d94:6210 before="64.0 GiB" now="64.0 GiB"
time=2025-02-22T20:51:31.658+08:00 level=DEBUG source=gpu.go:359 msg="updating system memory data" before.total="503.4 GiB" before.free="475.4 GiB" before.free_swap="15.4 GiB" now.total="503.4 GiB" now.free="475.4 GiB" now.free_swap="15.4 GiB"
time=2025-02-22T20:51:31.658+08:00 level=DEBUG source=amd_linux.go:440 msg="updating rocm free memory" gpu=5 name=1d94:6210 before="64.0 GiB" now="64.0 GiB"
time=2025-02-22T20:51:31.908+08:00 level=DEBUG source=gpu.go:359 msg="updating system memory data" before.total="503.4 GiB" before.free="475.4 GiB" before.free_swap="15.4 GiB" now.total="503.4 GiB" now.free="475.4 GiB" now.free_swap="15.4 GiB"
time=2025-02-22T20:51:31.909+08:00 level=DEBUG source=amd_linux.go:440 msg="updating rocm free memory" gpu=5 name=1d94:6210 before="64.0 GiB" now="64.0 GiB"
time=2025-02-22T20:51:32.158+08:00 level=WARN source=sched.go:647 msg="gpu VRAM usage didn't recover within timeout" seconds=5.001550841 model=/root/.ollama/models/blobs/sha256-1b93e4b8552fa16f44b7ee8e6f94df0a0e9abe9727f45d48db9af6cab651bb5a
time=2025-02-22T20:51:32.158+08:00 level=DEBUG source=sched.go:385 msg="sending an unloaded event" modelPath=/root/.ollama/models/blobs/sha256-1b93e4b8552fa16f44b7ee8e6f94df0a0e9abe9727f45d48db9af6cab651bb5a
time=2025-02-22T20:51:32.158+08:00 level=DEBUG source=sched.go:308 msg="ignoring unload event with no pending requests"
time=2025-02-22T20:51:32.158+08:00 level=DEBUG source=gpu.go:359 msg="updating system memory data" before.total="503.4 GiB" before.free="475.4 GiB" before.free_swap="15.4 GiB" now.total="503.4 GiB" now.free="475.4 GiB" now.free_swap="15.4 GiB"
time=2025-02-22T20:51:32.159+08:00 level=DEBUG source=amd_linux.go:440 msg="updating rocm free memory" gpu=5 name=1d94:6210 before="64.0 GiB" now="64.0 GiB"
time=2025-02-22T20:51:32.408+08:00 level=WARN source=sched.go:647 msg="gpu VRAM usage didn't recover within timeout" seconds=5.251668218 model=/root/.ollama/models/blobs/sha256-1b93e4b8552fa16f44b7ee8e6f94df0a0e9abe9727f45d48db9af6cab651bb5a
time=2025-02-22T20:51:32.409+08:00 level=DEBUG source=gpu.go:359 msg="updating system memory data" before.total="503.4 GiB" before.free="475.4 GiB" before.free_swap="15.4 GiB" now.total="503.4 GiB" now.free="475.4 GiB" now.free_swap="15.4 GiB"
time=2025-02-22T20:51:32.409+08:00 level=DEBUG source=amd_linux.go:440 msg="updating rocm free memory" gpu=5 name=1d94:6210 before="64.0 GiB" now="64.0 GiB"
time=2025-02-22T20:51:32.657+08:00 level=WARN source=sched.go:647 msg="gpu VRAM usage didn't recover within timeout" seconds=5.5010965 model=/root/.ollama/models/blobs/sha256-1b93e4b8552fa16f44b7ee8e6f94df0a0e9abe9727f45d48db9af6cab651bb5a

OS

Linux

GPU

Other

CPU

Intel

Ollama version

No response

Originally created by @wangzd0209 on GitHub (Feb 22, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9291 ### What is the issue? cmd ./ollama run test-qwen-0.5 when I want to run ollama i find it cannot know the device what is the problem? PS when i run ./ollama -version the version is 0.0.0 ### Relevant log output ```shell time=2025-02-22T20:51:27.157+08:00 level=DEBUG source=gpu.go:359 msg="updating system memory data" before.total="503.4 GiB" before.free="475.4 GiB" before.free_swap="15.4 GiB" now.total="503.4 GiB" now.free="475.4 GiB" now.free_swap="15.4 GiB" time=2025-02-22T20:51:27.157+08:00 level=DEBUG source=amd_linux.go:440 msg="updating rocm free memory" gpu=5 name=1d94:6210 before="64.0 GiB" now="64.0 GiB" time=2025-02-22T20:51:27.157+08:00 level=DEBUG source=server.go:1047 msg="stopping llama server" time=2025-02-22T20:51:27.157+08:00 level=DEBUG source=sched.go:381 msg="runner released" modelPath=/root/.ollama/models/blobs/sha256-1b93e4b8552fa16f44b7ee8e6f94df0a0e9abe9727f45d48db9af6cab651bb5a time=2025-02-22T20:51:27.408+08:00 level=DEBUG source=gpu.go:359 msg="updating system memory data" before.total="503.4 GiB" before.free="475.4 GiB" before.free_swap="15.4 GiB" now.total="503.4 GiB" now.free="475.4 GiB" now.free_swap="15.4 GiB" time=2025-02-22T20:51:27.409+08:00 level=DEBUG source=amd_linux.go:440 msg="updating rocm free memory" gpu=5 name=1d94:6210 before="64.0 GiB" now="64.0 GiB" time=2025-02-22T20:51:27.659+08:00 level=DEBUG source=gpu.go:359 msg="updating system memory data" before.total="503.4 GiB" before.free="475.4 GiB" before.free_swap="15.4 GiB" now.total="503.4 GiB" now.free="475.4 GiB" now.free_swap="15.4 GiB" time=2025-02-22T20:51:27.659+08:00 level=DEBUG source=amd_linux.go:440 msg="updating rocm free memory" gpu=5 name=1d94:6210 before="64.0 GiB" now="64.0 GiB" time=2025-02-22T20:51:27.909+08:00 level=DEBUG source=gpu.go:359 msg="updating system memory data" before.total="503.4 GiB" before.free="475.4 GiB" before.free_swap="15.4 GiB" now.total="503.4 GiB" now.free="475.4 GiB" now.free_swap="15.4 GiB" time=2025-02-22T20:51:27.909+08:00 level=DEBUG source=amd_linux.go:440 msg="updating rocm free memory" gpu=5 name=1d94:6210 before="64.0 GiB" now="64.0 GiB" time=2025-02-22T20:51:28.159+08:00 level=DEBUG source=gpu.go:359 msg="updating system memory data" before.total="503.4 GiB" before.free="475.4 GiB" before.free_swap="15.4 GiB" now.total="503.4 GiB" now.free="475.4 GiB" now.free_swap="15.4 GiB" time=2025-02-22T20:51:28.159+08:00 level=DEBUG source=amd_linux.go:440 msg="updating rocm free memory" gpu=5 name=1d94:6210 before="64.0 GiB" now="64.0 GiB" time=2025-02-22T20:51:28.409+08:00 level=DEBUG source=gpu.go:359 msg="updating system memory data" before.total="503.4 GiB" before.free="475.4 GiB" before.free_swap="15.4 GiB" now.total="503.4 GiB" now.free="475.4 GiB" now.free_swap="15.4 GiB" time=2025-02-22T20:51:28.409+08:00 level=DEBUG source=amd_linux.go:440 msg="updating rocm free memory" gpu=5 name=1d94:6210 before="64.0 GiB" now="64.0 GiB" time=2025-02-22T20:51:28.659+08:00 level=DEBUG source=gpu.go:359 msg="updating system memory data" before.total="503.4 GiB" before.free="475.4 GiB" before.free_swap="15.4 GiB" now.total="503.4 GiB" now.free="475.4 GiB" now.free_swap="15.4 GiB" time=2025-02-22T20:51:28.659+08:00 level=DEBUG source=amd_linux.go:440 msg="updating rocm free memory" gpu=5 name=1d94:6210 before="64.0 GiB" now="64.0 GiB" time=2025-02-22T20:51:28.909+08:00 level=DEBUG source=gpu.go:359 msg="updating system memory data" before.total="503.4 GiB" before.free="475.4 GiB" before.free_swap="15.4 GiB" now.total="503.4 GiB" now.free="475.4 GiB" now.free_swap="15.4 GiB" time=2025-02-22T20:51:28.909+08:00 level=DEBUG source=amd_linux.go:440 msg="updating rocm free memory" gpu=5 name=1d94:6210 before="64.0 GiB" now="64.0 GiB" time=2025-02-22T20:51:29.158+08:00 level=DEBUG source=gpu.go:359 msg="updating system memory data" before.total="503.4 GiB" before.free="475.4 GiB" before.free_swap="15.4 GiB" now.total="503.4 GiB" now.free="475.4 GiB" now.free_swap="15.4 GiB" time=2025-02-22T20:51:29.158+08:00 level=DEBUG source=amd_linux.go:440 msg="updating rocm free memory" gpu=5 name=1d94:6210 before="64.0 GiB" now="64.0 GiB" time=2025-02-22T20:51:29.408+08:00 level=DEBUG source=gpu.go:359 msg="updating system memory data" before.total="503.4 GiB" before.free="475.4 GiB" before.free_swap="15.4 GiB" now.total="503.4 GiB" now.free="475.4 GiB" now.free_swap="15.4 GiB" time=2025-02-22T20:51:29.409+08:00 level=DEBUG source=amd_linux.go:440 msg="updating rocm free memory" gpu=5 name=1d94:6210 before="64.0 GiB" now="64.0 GiB" time=2025-02-22T20:51:29.659+08:00 level=DEBUG source=gpu.go:359 msg="updating system memory data" before.total="503.4 GiB" before.free="475.4 GiB" before.free_swap="15.4 GiB" now.total="503.4 GiB" now.free="475.4 GiB" now.free_swap="15.4 GiB" time=2025-02-22T20:51:29.659+08:00 level=DEBUG source=amd_linux.go:440 msg="updating rocm free memory" gpu=5 name=1d94:6210 before="64.0 GiB" now="64.0 GiB" time=2025-02-22T20:51:29.909+08:00 level=DEBUG source=gpu.go:359 msg="updating system memory data" before.total="503.4 GiB" before.free="475.4 GiB" before.free_swap="15.4 GiB" now.total="503.4 GiB" now.free="475.4 GiB" now.free_swap="15.4 GiB" time=2025-02-22T20:51:29.909+08:00 level=DEBUG source=amd_linux.go:440 msg="updating rocm free memory" gpu=5 name=1d94:6210 before="64.0 GiB" now="64.0 GiB" time=2025-02-22T20:51:30.159+08:00 level=DEBUG source=gpu.go:359 msg="updating system memory data" before.total="503.4 GiB" before.free="475.4 GiB" before.free_swap="15.4 GiB" now.total="503.4 GiB" now.free="475.4 GiB" now.free_swap="15.4 GiB" time=2025-02-22T20:51:30.159+08:00 level=DEBUG source=amd_linux.go:440 msg="updating rocm free memory" gpu=5 name=1d94:6210 before="64.0 GiB" now="64.0 GiB" time=2025-02-22T20:51:30.408+08:00 level=DEBUG source=gpu.go:359 msg="updating system memory data" before.total="503.4 GiB" before.free="475.4 GiB" before.free_swap="15.4 GiB" now.total="503.4 GiB" now.free="475.4 GiB" now.free_swap="15.4 GiB" time=2025-02-22T20:51:30.408+08:00 level=DEBUG source=amd_linux.go:440 msg="updating rocm free memory" gpu=5 name=1d94:6210 before="64.0 GiB" now="64.0 GiB" time=2025-02-22T20:51:30.658+08:00 level=DEBUG source=gpu.go:359 msg="updating system memory data" before.total="503.4 GiB" before.free="475.4 GiB" before.free_swap="15.4 GiB" now.total="503.4 GiB" now.free="475.4 GiB" now.free_swap="15.4 GiB" time=2025-02-22T20:51:30.658+08:00 level=DEBUG source=amd_linux.go:440 msg="updating rocm free memory" gpu=5 name=1d94:6210 before="64.0 GiB" now="64.0 GiB" time=2025-02-22T20:51:30.908+08:00 level=DEBUG source=gpu.go:359 msg="updating system memory data" before.total="503.4 GiB" before.free="475.4 GiB" before.free_swap="15.4 GiB" now.total="503.4 GiB" now.free="475.4 GiB" now.free_swap="15.4 GiB" time=2025-02-22T20:51:30.908+08:00 level=DEBUG source=amd_linux.go:440 msg="updating rocm free memory" gpu=5 name=1d94:6210 before="64.0 GiB" now="64.0 GiB" time=2025-02-22T20:51:31.158+08:00 level=DEBUG source=gpu.go:359 msg="updating system memory data" before.total="503.4 GiB" before.free="475.4 GiB" before.free_swap="15.4 GiB" now.total="503.4 GiB" now.free="475.4 GiB" now.free_swap="15.4 GiB" time=2025-02-22T20:51:31.158+08:00 level=DEBUG source=amd_linux.go:440 msg="updating rocm free memory" gpu=5 name=1d94:6210 before="64.0 GiB" now="64.0 GiB" time=2025-02-22T20:51:31.408+08:00 level=DEBUG source=gpu.go:359 msg="updating system memory data" before.total="503.4 GiB" before.free="475.4 GiB" before.free_swap="15.4 GiB" now.total="503.4 GiB" now.free="475.4 GiB" now.free_swap="15.4 GiB" time=2025-02-22T20:51:31.408+08:00 level=DEBUG source=amd_linux.go:440 msg="updating rocm free memory" gpu=5 name=1d94:6210 before="64.0 GiB" now="64.0 GiB" time=2025-02-22T20:51:31.658+08:00 level=DEBUG source=gpu.go:359 msg="updating system memory data" before.total="503.4 GiB" before.free="475.4 GiB" before.free_swap="15.4 GiB" now.total="503.4 GiB" now.free="475.4 GiB" now.free_swap="15.4 GiB" time=2025-02-22T20:51:31.658+08:00 level=DEBUG source=amd_linux.go:440 msg="updating rocm free memory" gpu=5 name=1d94:6210 before="64.0 GiB" now="64.0 GiB" time=2025-02-22T20:51:31.908+08:00 level=DEBUG source=gpu.go:359 msg="updating system memory data" before.total="503.4 GiB" before.free="475.4 GiB" before.free_swap="15.4 GiB" now.total="503.4 GiB" now.free="475.4 GiB" now.free_swap="15.4 GiB" time=2025-02-22T20:51:31.909+08:00 level=DEBUG source=amd_linux.go:440 msg="updating rocm free memory" gpu=5 name=1d94:6210 before="64.0 GiB" now="64.0 GiB" time=2025-02-22T20:51:32.158+08:00 level=WARN source=sched.go:647 msg="gpu VRAM usage didn't recover within timeout" seconds=5.001550841 model=/root/.ollama/models/blobs/sha256-1b93e4b8552fa16f44b7ee8e6f94df0a0e9abe9727f45d48db9af6cab651bb5a time=2025-02-22T20:51:32.158+08:00 level=DEBUG source=sched.go:385 msg="sending an unloaded event" modelPath=/root/.ollama/models/blobs/sha256-1b93e4b8552fa16f44b7ee8e6f94df0a0e9abe9727f45d48db9af6cab651bb5a time=2025-02-22T20:51:32.158+08:00 level=DEBUG source=sched.go:308 msg="ignoring unload event with no pending requests" time=2025-02-22T20:51:32.158+08:00 level=DEBUG source=gpu.go:359 msg="updating system memory data" before.total="503.4 GiB" before.free="475.4 GiB" before.free_swap="15.4 GiB" now.total="503.4 GiB" now.free="475.4 GiB" now.free_swap="15.4 GiB" time=2025-02-22T20:51:32.159+08:00 level=DEBUG source=amd_linux.go:440 msg="updating rocm free memory" gpu=5 name=1d94:6210 before="64.0 GiB" now="64.0 GiB" time=2025-02-22T20:51:32.408+08:00 level=WARN source=sched.go:647 msg="gpu VRAM usage didn't recover within timeout" seconds=5.251668218 model=/root/.ollama/models/blobs/sha256-1b93e4b8552fa16f44b7ee8e6f94df0a0e9abe9727f45d48db9af6cab651bb5a time=2025-02-22T20:51:32.409+08:00 level=DEBUG source=gpu.go:359 msg="updating system memory data" before.total="503.4 GiB" before.free="475.4 GiB" before.free_swap="15.4 GiB" now.total="503.4 GiB" now.free="475.4 GiB" now.free_swap="15.4 GiB" time=2025-02-22T20:51:32.409+08:00 level=DEBUG source=amd_linux.go:440 msg="updating rocm free memory" gpu=5 name=1d94:6210 before="64.0 GiB" now="64.0 GiB" time=2025-02-22T20:51:32.657+08:00 level=WARN source=sched.go:647 msg="gpu VRAM usage didn't recover within timeout" seconds=5.5010965 model=/root/.ollama/models/blobs/sha256-1b93e4b8552fa16f44b7ee8e6f94df0a0e9abe9727f45d48db9af6cab651bb5a ``` ### OS Linux ### GPU Other ### CPU Intel ### Ollama version _No response_
GiteaMirror added the bug label 2026-04-12 17:23:14 -05:00
GiteaMirror commented 2026-04-12 17:23:15 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 22, 2025):

time=2025-02-22T20:51:32.657+08:00 level=WARN source=sched.go:647 msg="gpu VRAM usage didn't recover within timeout" seconds=5.5010965 model=/root/.ollama/models/blobs/sha256-1b93e4b8552fa16f44b7ee8e6f94df0a0e9abe9727f45d48db9af6cab651bb5a

Just a warning, you can ignore it.

PS when i run ./ollama -version the version is 0.0.0

Because you compiled from source.

Error: llama runner process has terminated: error:Could not initialize Tensile host: No devices found

The log doesn't contain enough information to debug this. Post full log.

<!-- gh-comment-id:2676220701 --> @rick-github commented on GitHub (Feb 22, 2025): ``` time=2025-02-22T20:51:32.657+08:00 level=WARN source=sched.go:647 msg="gpu VRAM usage didn't recover within timeout" seconds=5.5010965 model=/root/.ollama/models/blobs/sha256-1b93e4b8552fa16f44b7ee8e6f94df0a0e9abe9727f45d48db9af6cab651bb5a ``` Just a warning, you can ignore it. > PS when i run ./ollama -version the version is 0.0.0 Because you compiled from source. ``` Error: llama runner process has terminated: error:Could not initialize Tensile host: No devices found ``` The log doesn't contain enough information to debug this. Post full log.
GiteaMirror commented 2026-04-12 17:23:16 -05:00
Author
Owner
Copy Link

@wangzd0209 commented on GitHub (Feb 23, 2025):

time=2025-02-22T20:51:32.657+08:00 level=WARN source=sched.go:647 msg="gpu VRAM usage didn't recover within timeout" seconds=5.5010965 model=/root/.ollama/models/blobs/sha256-1b93e4b8552fa16f44b7ee8e6f94df0a0e9abe9727f45d48db9af6cab651bb5a

Just a warning, you can ignore it.

PS when i run ./ollama -version the version is 0.0.0

Because you compiled from source.

Error: llama runner process has terminated: error:Could not initialize Tensile host: No devices found

The log doesn't contain enough information to debug this. Post full log.

when I use sudo ./ollama serve anything is ok but when i use ./ollama serve it show this problem what happen? or some cmd can handle that?

<!-- gh-comment-id:2676550552 --> @wangzd0209 commented on GitHub (Feb 23, 2025): > ``` > time=2025-02-22T20:51:32.657+08:00 level=WARN source=sched.go:647 msg="gpu VRAM usage didn't recover within timeout" seconds=5.5010965 model=/root/.ollama/models/blobs/sha256-1b93e4b8552fa16f44b7ee8e6f94df0a0e9abe9727f45d48db9af6cab651bb5a > ``` > > Just a warning, you can ignore it. > > > PS when i run ./ollama -version the version is 0.0.0 > > Because you compiled from source. > > ``` > Error: llama runner process has terminated: error:Could not initialize Tensile host: No devices found > ``` > > The log doesn't contain enough information to debug this. Post full log. when I use sudo ./ollama serve anything is ok but when i use ./ollama serve it show this problem what happen? or some cmd can handle that?
GiteaMirror commented 2026-04-12 17:23:17 -05:00
Author
Owner
Copy Link

@wangzd0209 commented on GitHub (Feb 23, 2025):

time=2025-02-22T20:51:32.657+08:00 level=WARN source=sched.go:647 msg="gpu VRAM usage didn't recover within timeout" seconds=5.5010965 model=/root/.ollama/models/blobs/sha256-1b93e4b8552fa16f44b7ee8e6f94df0a0e9abe9727f45d48db9af6cab651bb5a

Just a warning, you can ignore it.

PS when i run ./ollama -version the version is 0.0.0

Because you compiled from source.

Error: llama runner process has terminated: error:Could not initialize Tensile host: No devices found

The log doesn't contain enough information to debug this. Post full log.

when I use sudo ./ollama serve anything is ok but when i use ./ollama serve it show this problem what happen? or some cmd can handle that?

<!-- gh-comment-id:2676550682 --> @wangzd0209 commented on GitHub (Feb 23, 2025): > ``` > time=2025-02-22T20:51:32.657+08:00 level=WARN source=sched.go:647 msg="gpu VRAM usage didn't recover within timeout" seconds=5.5010965 model=/root/.ollama/models/blobs/sha256-1b93e4b8552fa16f44b7ee8e6f94df0a0e9abe9727f45d48db9af6cab651bb5a > ``` > > Just a warning, you can ignore it. > > > PS when i run ./ollama -version the version is 0.0.0 > > Because you compiled from source. > > ``` > Error: llama runner process has terminated: error:Could not initialize Tensile host: No devices found > ``` > > The log doesn't contain enough information to debug this. Post full log. when I use sudo ./ollama serve anything is ok but when i use ./ollama serve it show this problem what happen? or some cmd can handle that?
GiteaMirror commented 2026-04-12 17:23:18 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 23, 2025):

Sounds like permissions issues: https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#amd-gpu-discovery

<!-- gh-comment-id:2676816405 --> @rick-github commented on GitHub (Feb 23, 2025): Sounds like permissions issues: https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#amd-gpu-discovery
GiteaMirror commented 2026-04-12 17:23:19 -05:00
Author
Owner
Copy Link

@wangzd0209 commented on GitHub (Feb 23, 2025):

Sounds like permissions issues: https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#amd-gpu-discovery

thanks for your help the problem maybe slove. And I can use ollama in my computer now.

<!-- gh-comment-id:2676866322 --> @wangzd0209 commented on GitHub (Feb 23, 2025): > Sounds like permissions issues: https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#amd-gpu-discovery thanks for your help the problem maybe slove. And I can use ollama in my computer now.
GiteaMirror commented 2026-04-12 17:23:19 -05:00
Author
Owner
Copy Link

@wangzd0209 commented on GitHub (Feb 24, 2025):

Sounds like permissions issues: https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#amd-gpu-discovery

today i find a special problem when i add video group in my machine ollama is good. But when i use a docker i found that the video gid is 39 out of container ,but i still found the video gid is 44 in a ubuntu container. What happen?

<!-- gh-comment-id:2678284901 --> @wangzd0209 commented on GitHub (Feb 24, 2025): > Sounds like permissions issues: https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#amd-gpu-discovery today i find a special problem when i add video group in my machine ollama is good. But when i use a docker i found that the video gid is 39 out of container ,but i still found the video gid is 44 in a ubuntu container. What happen?
GiteaMirror commented 2026-04-12 17:23:20 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 24, 2025):

The /etc/group file is different inside the container compared to outside the container.

<!-- gh-comment-id:2678517430 --> @rick-github commented on GitHub (Feb 24, 2025): The `/etc/group` file is different inside the container compared to outside the container.
GiteaMirror commented 2026-04-12 17:23:21 -05:00
Author
Owner
Copy Link

@wangzd0209 commented on GitHub (Feb 24, 2025):

The /etc/group file is different inside the container compared to outside the container.

did you fix that ？because i can use ollama in recently version but i can not use ollama in eraly version like 0.3.5

<!-- gh-comment-id:2678536667 --> @wangzd0209 commented on GitHub (Feb 24, 2025): > The `/etc/group` file is different inside the container compared to outside the container. did you fix that ？because i can use ollama in recently version but i can not use ollama in eraly version like 0.3.5
GiteaMirror commented 2026-04-12 17:23:22 -05:00
Author
Owner
Copy Link

@wangzd0209 commented on GitHub (Feb 24, 2025):

The /etc/group file is different inside the container compared to outside the container.

so container transfer the group id by itself? like 44 inside to 39 outside right?

<!-- gh-comment-id:2678553356 --> @wangzd0209 commented on GitHub (Feb 24, 2025): > The `/etc/group` file is different inside the container compared to outside the container. so container transfer the group id by itself? like 44 inside to 39 outside right?
GiteaMirror commented 2026-04-12 17:23:22 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 24, 2025):

If you want to control the uid/gid of the program in the container, use the --user docker command line option or the user docker compose field.

<!-- gh-comment-id:2678607383 --> @rick-github commented on GitHub (Feb 24, 2025): If you want to control the uid/gid of the program in the container, use the [`--user`](https://docs.docker.com/engine/containers/run/#user) docker command line option or the [`user`](https://docs.docker.com/reference/compose-file/services/#user) docker compose field.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#6059
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?