github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #12006] ollama容器跑gpt-oss模型时，显卡莫名丢失了 #54485

New Issue
Closed
opened 2026-04-29 06:07:03 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-29 06:07:03 -05:00
Owner
Copy Link

Originally created by @main1015 on GitHub (Aug 21, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12006

What is the issue?

我使用ollama容器跑gpt-oss:20b模型时，显卡莫名丢失了，在容器里面执行：

root@ad006a655920:/# nvidia-smi
Failed to initialize NVML: Unknown Error

我ollama容器镜像是：

(base) wy@myth:~$ docker images |grep ollama
ollama/ollama                                                       latest          53f18253db46   2 weeks ago     2.28GB

这是什么情况？？？
下面是我ollama容器的日志：

load_backend: loaded CUDA backend from /usr/lib/ollama/libggml-cuda.so
load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-alderlake.so
time=2025-08-08T02:05:57.655Z level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,600,610,700,750,800,860,870,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(gcc)
time=2025-08-08T02:05:57.742Z level=INFO source=ggml.go:367 msg="offloading 24 repeating layers to GPU"
time=2025-08-08T02:05:57.742Z level=INFO source=ggml.go:371 msg="offloading output layer to CPU"
time=2025-08-08T02:05:57.742Z level=INFO source=ggml.go:378 msg="offloaded 24/25 layers to GPU"
time=2025-08-08T02:05:57.742Z level=INFO source=ggml.go:381 msg="model weights" buffer=CUDA0 size="10.7 GiB"
time=2025-08-08T02:05:57.742Z level=INFO source=ggml.go:381 msg="model weights" buffer=CPU size="2.2 GiB"
time=2025-08-08T02:05:57.750Z level=INFO source=ggml.go:672 msg="compute graph" backend=CUDA0 buffer_type=CUDA0 size="8.1 GiB"
time=2025-08-08T02:05:57.750Z level=INFO source=ggml.go:672 msg="compute graph" backend=CPU buffer_type=CPU size="5.6 MiB"
time=2025-08-08T02:05:57.801Z level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model"
time=2025-08-08T02:06:00.814Z level=INFO source=server.go:637 msg="llama runner started in 3.26 seconds"
[GIN] 2025/08/08 - 02:06:12 | 200 |      22.763µs |       127.0.0.1 | HEAD     "/"
[GIN] 2025/08/08 - 02:06:12 | 200 |      25.861µs |       127.0.0.1 | GET      "/api/ps"
[GIN] 2025/08/08 - 02:07:14 | 200 |         1m18s |      172.17.0.1 | POST     "/v1/chat/completions"
[GIN] 2025/08/08 - 02:07:46 | 200 |      21.995µs |       127.0.0.1 | HEAD     "/"
[GIN] 2025/08/08 - 02:07:46 | 200 |      23.404µs |       127.0.0.1 | GET      "/api/ps"
[GIN] 2025/08/08 - 02:07:47 | 200 |      35.693µs |       127.0.0.1 | HEAD     "/"
[GIN] 2025/08/08 - 02:07:47 | 200 |       28.29µs |       127.0.0.1 | GET      "/api/ps"
[GIN] 2025/08/08 - 02:09:41 | 200 |      41.661µs |       127.0.0.1 | HEAD     "/"
[GIN] 2025/08/08 - 02:09:41 | 200 |      73.833µs |       127.0.0.1 | GET      "/api/ps"
[GIN] 2025/08/08 - 02:15:40 | 404 |     948.688µs |      172.17.0.1 | POST     "/api/generate"
[GIN] 2025/08/08 - 02:15:42 | 404 |     795.312µs |      172.17.0.1 | POST     "/api/generate"
time=2025-08-08T02:15:42.418Z level=INFO source=server.go:135 msg="system memory" total="125.5 GiB" free="101.6 GiB" free_swap="2.0 GiB"
time=2025-08-08T02:15:42.418Z level=INFO source=server.go:175 msg=offload library=cuda layers.requested=-1 layers.model=25 layers.offload=0 layers.split="" memory.available="[21.5 GiB]" memory.gpu_overhead="0 B" memory.required.full="15.1 GiB" memory.required.partial="0 B" memory.required.kv="3.4 GiB" memory.required.allocations="[0 B]" memory.weights.total="11.7 GiB" memory.weights.repeating="10.7 GiB" memory.weights.nonrepeating="1.1 GiB" memory.graph.full="32.0 GiB" memory.graph.partial="32.0 GiB"
time=2025-08-08T02:15:42.459Z level=INFO source=server.go:438 msg="starting llama server" cmd="/usr/bin/ollama runner --ollama-engine --model /root/.ollama/models/blobs/sha256-b112e727c6f18875636c56a779790a590d705aec9e1c0eb5a97d51fc2a778583 --ctx-size 131072 --batch-size 512 --threads 8 --no-mmap --parallel 4 --port 34903"
time=2025-08-08T02:15:42.459Z level=INFO source=sched.go:481 msg="loaded runners" count=1
time=2025-08-08T02:15:42.459Z level=INFO source=server.go:598 msg="waiting for llama runner to start responding"
time=2025-08-08T02:15:42.459Z level=WARN source=server.go:605 msg="client connection closed before server finished loading, aborting load"
time=2025-08-08T02:15:42.459Z level=ERROR source=sched.go:487 msg="error loading llama server" error="timed out waiting for llama runner to start: context canceled"
[GIN] 2025/08/08 - 02:15:42 | 499 |  1.182658609s |      172.17.0.1 | POST     "/api/generate"
time=2025-08-08T02:15:42.468Z level=INFO source=runner.go:925 msg="starting ollama engine"
time=2025-08-08T02:15:42.469Z level=INFO source=runner.go:983 msg="Server listening on 127.0.0.1:34903"
time=2025-08-08T02:15:42.512Z level=INFO source=ggml.go:92 msg="" architecture=gptoss file_type=MXFP4 name="" description="" num_tensors=315 num_key_values=30
ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
  Device 0: NVIDIA RTX A5000, compute capability 8.6, VMM: yes
load_backend: loaded CUDA backend from /usr/lib/ollama/libggml-cuda.so
load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-alderlake.so
time=2025-08-08T02:15:42.598Z level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,600,610,700,750,800,860,870,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(gcc)
time=2025-08-08T02:15:43.353Z level=INFO source=server.go:135 msg="system memory" total="125.5 GiB" free="101.6 GiB" free_swap="2.0 GiB"
time=2025-08-08T02:15:43.354Z level=INFO source=server.go:175 msg=offload library=cuda layers.requested=-1 layers.model=25 layers.offload=0 layers.split="" memory.available="[21.5 GiB]" memory.gpu_overhead="0 B" memory.required.full="15.1 GiB" memory.required.partial="0 B" memory.required.kv="3.4 GiB" memory.required.allocations="[0 B]" memory.weights.total="11.7 GiB" memory.weights.repeating="10.7 GiB" memory.weights.nonrepeating="1.1 GiB" memory.graph.full="32.0 GiB" memory.graph.partial="32.0 GiB"
time=2025-08-08T02:15:43.397Z level=INFO source=server.go:438 msg="starting llama server" cmd="/usr/bin/ollama runner --ollama-engine --model /root/.ollama/models/blobs/sha256-b112e727c6f18875636c56a779790a590d705aec9e1c0eb5a97d51fc2a778583 --ctx-size 131072 --batch-size 512 --threads 8 --no-mmap --parallel 4 --port 42821"
time=2025-08-08T02:15:43.397Z level=INFO source=sched.go:481 msg="loaded runners" count=1
time=2025-08-08T02:15:43.397Z level=INFO source=server.go:598 msg="waiting for llama runner to start responding"
time=2025-08-08T02:15:43.397Z level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding"
time=2025-08-08T02:15:43.406Z level=INFO source=runner.go:925 msg="starting ollama engine"
time=2025-08-08T02:15:43.406Z level=INFO source=runner.go:983 msg="Server listening on 127.0.0.1:42821"
time=2025-08-08T02:15:43.449Z level=INFO source=ggml.go:92 msg="" architecture=gptoss file_type=MXFP4 name="" description="" num_tensors=315 num_key_values=30
ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
  Device 0: NVIDIA RTX A5000, compute capability 8.6, VMM: yes
load_backend: loaded CUDA backend from /usr/lib/ollama/libggml-cuda.so
load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-alderlake.so
time=2025-08-08T02:15:43.501Z level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,600,610,700,750,800,860,870,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(gcc)
time=2025-08-08T02:15:43.588Z level=INFO source=ggml.go:367 msg="offloading 0 repeating layers to GPU"
time=2025-08-08T02:15:43.588Z level=INFO source=ggml.go:371 msg="offloading output layer to CPU"
time=2025-08-08T02:15:43.588Z level=INFO source=ggml.go:378 msg="offloaded 0/25 layers to GPU"
time=2025-08-08T02:15:43.588Z level=INFO source=ggml.go:381 msg="model weights" buffer=CPU size="12.8 GiB"
time=2025-08-08T02:15:43.648Z level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model"
time=2025-08-08T02:15:44.647Z level=INFO source=ggml.go:672 msg="compute graph" backend=CUDA0 buffer_type=CUDA0 size="0 B"
time=2025-08-08T02:15:44.647Z level=INFO source=ggml.go:672 msg="compute graph" backend=CPU buffer_type=CPU size="32.0 GiB"
time=2025-08-08T02:15:45.909Z level=INFO source=server.go:637 msg="llama runner started in 2.51 seconds"
[GIN] 2025/08/08 - 02:15:46 | 404 |     842.099µs |      172.17.0.1 | POST     "/api/generate"
[GIN] 2025/08/08 - 02:15:46 | 404 |     835.145µs |      172.17.0.1 | POST     "/api/generate"
time=2025-08-08T02:15:46.720Z level=ERROR source=server.go:807 msg="post predict" error="Post \"http://127.0.0.1:42821/completion\": context canceled"
[GIN] 2025/08/08 - 02:15:46 | 200 |  4.337180182s |      172.17.0.1 | POST     "/api/generate"
[GIN] 2025/08/08 - 02:15:48 | 404 |     797.596µs |      172.17.0.1 | POST     "/api/generate"
[GIN] 2025/08/08 - 02:15:48 | 404 |     821.356µs |      172.17.0.1 | POST     "/api/generate"
time=2025-08-08T02:15:49.021Z level=ERROR source=server.go:807 msg="post predict" error="Post \"http://127.0.0.1:42821/completion\": context canceled"
[GIN] 2025/08/08 - 02:15:49 | 200 |  2.272718522s |      172.17.0.1 | POST     "/api/generate"
[GIN] 2025/08/08 - 02:15:49 | 404 |     820.049µs |      172.17.0.1 | POST     "/api/generate"
time=2025-08-08T02:15:49.657Z level=ERROR source=server.go:807 msg="post predict" error="Post \"http://127.0.0.1:42821/completion\": context canceled"
[GIN] 2025/08/08 - 02:15:49 | 200 |  606.929414ms |      172.17.0.1 | POST     "/api/generate"
[GIN] 2025/08/08 - 02:15:52 | 404 |     783.625µs |      172.17.0.1 | POST     "/api/generate"
time=2025-08-08T02:15:53.306Z level=ERROR source=server.go:807 msg="post predict" error="Post \"http://127.0.0.1:42821/completion\": context canceled"
[GIN] 2025/08/08 - 02:15:53 | 200 |  3.622453821s |      172.17.0.1 | POST     "/api/generate"
[GIN] 2025/08/08 - 02:15:53 | 200 |  101.029513ms |      172.17.0.1 | POST     "/api/show"
[GIN] 2025/08/08 - 02:15:54 | 200 |   78.520838ms |      172.17.0.1 | POST     "/api/show"
[GIN] 2025/08/08 - 02:15:55 | 200 |  100.599109ms |      172.17.0.1 | POST     "/api/show"
[GIN] 2025/08/08 - 02:15:55 | 200 |    99.47526ms |      172.17.0.1 | POST     "/api/show"
[GIN] 2025/08/08 - 02:15:55 | 200 |  101.515257ms |      172.17.0.1 | POST     "/api/show"
[GIN] 2025/08/08 - 02:16:40 | 200 |      27.406µs |       127.0.0.1 | HEAD     "/"
[GIN] 2025/08/08 - 02:16:40 | 200 |      30.508µs |       127.0.0.1 | GET      "/api/ps"
[GIN] 2025/08/08 - 02:17:05 | 200 |       22.33µs |       127.0.0.1 | HEAD     "/"
[GIN] 2025/08/08 - 02:17:05 | 200 |      21.118µs |       127.0.0.1 | GET      "/api/ps"
[GIN] 2025/08/08 - 02:17:47 | 200 |      24.005µs |       127.0.0.1 | HEAD     "/"
[GIN] 2025/08/08 - 02:17:47 | 200 |      27.324µs |       127.0.0.1 | GET      "/api/ps"
[GIN] 2025/08/08 - 02:17:48 | 200 |      24.076µs |       127.0.0.1 | HEAD     "/"
[GIN] 2025/08/08 - 02:17:48 | 200 |      24.453µs |       127.0.0.1 | GET      "/api/ps"
[GIN] 2025/08/08 - 02:18:36 | 200 |      31.943µs |       127.0.0.1 | HEAD     "/"
[GIN] 2025/08/08 - 02:18:36 | 200 |      39.346µs |       127.0.0.1 | GET      "/api/ps"
[GIN] 2025/08/08 - 02:18:37 | 200 |       23.75µs |       127.0.0.1 | HEAD     "/"
[GIN] 2025/08/08 - 02:18:37 | 200 |      34.403µs |       127.0.0.1 | GET      "/api/ps"
time=2025-08-08T02:18:39.424Z level=ERROR source=server.go:807 msg="post predict" error="Post \"http://127.0.0.1:42821/completion\": context canceled"
time=2025-08-08T02:18:39.424Z level=INFO source=runner.go:646 msg="aborting completion request due to client closing the connection"
[GIN] 2025/08/08 - 02:18:39 | 200 |         2m46s |      172.17.0.1 | POST     "/api/generate"
[GIN] 2025/08/08 - 02:19:15 | 200 |      28.224µs |      172.17.0.1 | GET      "/"
[GIN] 2025/08/08 - 02:19:15 | 404 |       5.403µs |      172.17.0.1 | GET      "/favicon.ico"
[GIN] 2025/08/08 - 02:19:37 | 200 |      21.216µs |       127.0.0.1 | HEAD     "/"
[GIN] 2025/08/08 - 02:19:37 | 200 |      23.773µs |       127.0.0.1 | GET      "/api/ps"
[GIN] 2025/08/08 - 02:19:37 | 200 |      22.829µs |       127.0.0.1 | HEAD     "/"
[GIN] 2025/08/08 - 02:19:37 | 200 |      22.603µs |       127.0.0.1 | GET      "/api/ps"
time=2025-08-08T02:21:19.309Z level=ERROR source=server.go:807 msg="post predict" error="Post \"http://127.0.0.1:42821/completion\": context canceled"
time=2025-08-08T02:21:19.309Z level=INFO source=runner.go:646 msg="aborting completion request due to client closing the connection"
[GIN] 2025/08/08 - 02:21:19 | 200 |         1m48s |      172.17.0.1 | POST     "/api/chat"
[GIN] 2025/08/08 - 02:21:42 | 200 |      21.686µs |       127.0.0.1 | HEAD     "/"
[GIN] 2025/08/08 - 02:21:42 | 200 |      23.775µs |       127.0.0.1 | GET      "/api/ps"
time=2025-08-08T02:21:48.022Z level=ERROR source=server.go:807 msg="post predict" error="Post \"http://127.0.0.1:42821/completion\": context canceled"
time=2025-08-08T02:21:48.022Z level=INFO source=runner.go:646 msg="aborting completion request due to client closing the connection"
[GIN] 2025/08/08 - 02:21:48 | 200 | 17.287678521s |      172.17.0.1 | POST     "/api/chat"
[GIN] 2025/08/08 - 02:23:22 | 200 |      21.187µs |       127.0.0.1 | HEAD     "/"
[GIN] 2025/08/08 - 02:23:22 | 200 |    1.270011ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2025/08/08 - 02:23:32 | 404 |     860.202µs |      172.17.0.1 | POST     "/api/generate"
[GIN] 2025/08/08 - 02:23:34 | 404 |     874.441µs |      172.17.0.1 | POST     "/api/generate"
time=2025-08-08T02:23:35.027Z level=ERROR source=server.go:807 msg="post predict" error="Post \"http://127.0.0.1:42821/completion\": context canceled"
time=2025-08-08T02:23:35.027Z level=INFO source=runner.go:646 msg="aborting completion request due to client closing the connection"

Relevant log output

OS

No response

GPU

No response

CPU

No response

Ollama version

No response

Originally created by @main1015 on GitHub (Aug 21, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12006 ### What is the issue? 我使用ollama容器跑gpt-oss:20b模型时，显卡莫名丢失了，在容器里面执行： ``` root@ad006a655920:/# nvidia-smi Failed to initialize NVML: Unknown Error ``` 我ollama容器镜像是： ``` (base) wy@myth:~$ docker images |grep ollama ollama/ollama latest 53f18253db46 2 weeks ago 2.28GB ``` 这是什么情况？？？ 下面是我ollama容器的日志： ``` load_backend: loaded CUDA backend from /usr/lib/ollama/libggml-cuda.so load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-alderlake.so time=2025-08-08T02:05:57.655Z level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,600,610,700,750,800,860,870,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(gcc) time=2025-08-08T02:05:57.742Z level=INFO source=ggml.go:367 msg="offloading 24 repeating layers to GPU" time=2025-08-08T02:05:57.742Z level=INFO source=ggml.go:371 msg="offloading output layer to CPU" time=2025-08-08T02:05:57.742Z level=INFO source=ggml.go:378 msg="offloaded 24/25 layers to GPU" time=2025-08-08T02:05:57.742Z level=INFO source=ggml.go:381 msg="model weights" buffer=CUDA0 size="10.7 GiB" time=2025-08-08T02:05:57.742Z level=INFO source=ggml.go:381 msg="model weights" buffer=CPU size="2.2 GiB" time=2025-08-08T02:05:57.750Z level=INFO source=ggml.go:672 msg="compute graph" backend=CUDA0 buffer_type=CUDA0 size="8.1 GiB" time=2025-08-08T02:05:57.750Z level=INFO source=ggml.go:672 msg="compute graph" backend=CPU buffer_type=CPU size="5.6 MiB" time=2025-08-08T02:05:57.801Z level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model" time=2025-08-08T02:06:00.814Z level=INFO source=server.go:637 msg="llama runner started in 3.26 seconds" [GIN] 2025/08/08 - 02:06:12 | 200 | 22.763µs | 127.0.0.1 | HEAD "/" [GIN] 2025/08/08 - 02:06:12 | 200 | 25.861µs | 127.0.0.1 | GET "/api/ps" [GIN] 2025/08/08 - 02:07:14 | 200 | 1m18s | 172.17.0.1 | POST "/v1/chat/completions" [GIN] 2025/08/08 - 02:07:46 | 200 | 21.995µs | 127.0.0.1 | HEAD "/" [GIN] 2025/08/08 - 02:07:46 | 200 | 23.404µs | 127.0.0.1 | GET "/api/ps" [GIN] 2025/08/08 - 02:07:47 | 200 | 35.693µs | 127.0.0.1 | HEAD "/" [GIN] 2025/08/08 - 02:07:47 | 200 | 28.29µs | 127.0.0.1 | GET "/api/ps" [GIN] 2025/08/08 - 02:09:41 | 200 | 41.661µs | 127.0.0.1 | HEAD "/" [GIN] 2025/08/08 - 02:09:41 | 200 | 73.833µs | 127.0.0.1 | GET "/api/ps" [GIN] 2025/08/08 - 02:15:40 | 404 | 948.688µs | 172.17.0.1 | POST "/api/generate" [GIN] 2025/08/08 - 02:15:42 | 404 | 795.312µs | 172.17.0.1 | POST "/api/generate" time=2025-08-08T02:15:42.418Z level=INFO source=server.go:135 msg="system memory" total="125.5 GiB" free="101.6 GiB" free_swap="2.0 GiB" time=2025-08-08T02:15:42.418Z level=INFO source=server.go:175 msg=offload library=cuda layers.requested=-1 layers.model=25 layers.offload=0 layers.split="" memory.available="[21.5 GiB]" memory.gpu_overhead="0 B" memory.required.full="15.1 GiB" memory.required.partial="0 B" memory.required.kv="3.4 GiB" memory.required.allocations="[0 B]" memory.weights.total="11.7 GiB" memory.weights.repeating="10.7 GiB" memory.weights.nonrepeating="1.1 GiB" memory.graph.full="32.0 GiB" memory.graph.partial="32.0 GiB" time=2025-08-08T02:15:42.459Z level=INFO source=server.go:438 msg="starting llama server" cmd="/usr/bin/ollama runner --ollama-engine --model /root/.ollama/models/blobs/sha256-b112e727c6f18875636c56a779790a590d705aec9e1c0eb5a97d51fc2a778583 --ctx-size 131072 --batch-size 512 --threads 8 --no-mmap --parallel 4 --port 34903" time=2025-08-08T02:15:42.459Z level=INFO source=sched.go:481 msg="loaded runners" count=1 time=2025-08-08T02:15:42.459Z level=INFO source=server.go:598 msg="waiting for llama runner to start responding" time=2025-08-08T02:15:42.459Z level=WARN source=server.go:605 msg="client connection closed before server finished loading, aborting load" time=2025-08-08T02:15:42.459Z level=ERROR source=sched.go:487 msg="error loading llama server" error="timed out waiting for llama runner to start: context canceled" [GIN] 2025/08/08 - 02:15:42 | 499 | 1.182658609s | 172.17.0.1 | POST "/api/generate" time=2025-08-08T02:15:42.468Z level=INFO source=runner.go:925 msg="starting ollama engine" time=2025-08-08T02:15:42.469Z level=INFO source=runner.go:983 msg="Server listening on 127.0.0.1:34903" time=2025-08-08T02:15:42.512Z level=INFO source=ggml.go:92 msg="" architecture=gptoss file_type=MXFP4 name="" description="" num_tensors=315 num_key_values=30 ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 1 CUDA devices: Device 0: NVIDIA RTX A5000, compute capability 8.6, VMM: yes load_backend: loaded CUDA backend from /usr/lib/ollama/libggml-cuda.so load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-alderlake.so time=2025-08-08T02:15:42.598Z level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,600,610,700,750,800,860,870,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(gcc) time=2025-08-08T02:15:43.353Z level=INFO source=server.go:135 msg="system memory" total="125.5 GiB" free="101.6 GiB" free_swap="2.0 GiB" time=2025-08-08T02:15:43.354Z level=INFO source=server.go:175 msg=offload library=cuda layers.requested=-1 layers.model=25 layers.offload=0 layers.split="" memory.available="[21.5 GiB]" memory.gpu_overhead="0 B" memory.required.full="15.1 GiB" memory.required.partial="0 B" memory.required.kv="3.4 GiB" memory.required.allocations="[0 B]" memory.weights.total="11.7 GiB" memory.weights.repeating="10.7 GiB" memory.weights.nonrepeating="1.1 GiB" memory.graph.full="32.0 GiB" memory.graph.partial="32.0 GiB" time=2025-08-08T02:15:43.397Z level=INFO source=server.go:438 msg="starting llama server" cmd="/usr/bin/ollama runner --ollama-engine --model /root/.ollama/models/blobs/sha256-b112e727c6f18875636c56a779790a590d705aec9e1c0eb5a97d51fc2a778583 --ctx-size 131072 --batch-size 512 --threads 8 --no-mmap --parallel 4 --port 42821" time=2025-08-08T02:15:43.397Z level=INFO source=sched.go:481 msg="loaded runners" count=1 time=2025-08-08T02:15:43.397Z level=INFO source=server.go:598 msg="waiting for llama runner to start responding" time=2025-08-08T02:15:43.397Z level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding" time=2025-08-08T02:15:43.406Z level=INFO source=runner.go:925 msg="starting ollama engine" time=2025-08-08T02:15:43.406Z level=INFO source=runner.go:983 msg="Server listening on 127.0.0.1:42821" time=2025-08-08T02:15:43.449Z level=INFO source=ggml.go:92 msg="" architecture=gptoss file_type=MXFP4 name="" description="" num_tensors=315 num_key_values=30 ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 1 CUDA devices: Device 0: NVIDIA RTX A5000, compute capability 8.6, VMM: yes load_backend: loaded CUDA backend from /usr/lib/ollama/libggml-cuda.so load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-alderlake.so time=2025-08-08T02:15:43.501Z level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,600,610,700,750,800,860,870,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(gcc) time=2025-08-08T02:15:43.588Z level=INFO source=ggml.go:367 msg="offloading 0 repeating layers to GPU" time=2025-08-08T02:15:43.588Z level=INFO source=ggml.go:371 msg="offloading output layer to CPU" time=2025-08-08T02:15:43.588Z level=INFO source=ggml.go:378 msg="offloaded 0/25 layers to GPU" time=2025-08-08T02:15:43.588Z level=INFO source=ggml.go:381 msg="model weights" buffer=CPU size="12.8 GiB" time=2025-08-08T02:15:43.648Z level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model" time=2025-08-08T02:15:44.647Z level=INFO source=ggml.go:672 msg="compute graph" backend=CUDA0 buffer_type=CUDA0 size="0 B" time=2025-08-08T02:15:44.647Z level=INFO source=ggml.go:672 msg="compute graph" backend=CPU buffer_type=CPU size="32.0 GiB" time=2025-08-08T02:15:45.909Z level=INFO source=server.go:637 msg="llama runner started in 2.51 seconds" [GIN] 2025/08/08 - 02:15:46 | 404 | 842.099µs | 172.17.0.1 | POST "/api/generate" [GIN] 2025/08/08 - 02:15:46 | 404 | 835.145µs | 172.17.0.1 | POST "/api/generate" time=2025-08-08T02:15:46.720Z level=ERROR source=server.go:807 msg="post predict" error="Post \"http://127.0.0.1:42821/completion\": context canceled" [GIN] 2025/08/08 - 02:15:46 | 200 | 4.337180182s | 172.17.0.1 | POST "/api/generate" [GIN] 2025/08/08 - 02:15:48 | 404 | 797.596µs | 172.17.0.1 | POST "/api/generate" [GIN] 2025/08/08 - 02:15:48 | 404 | 821.356µs | 172.17.0.1 | POST "/api/generate" time=2025-08-08T02:15:49.021Z level=ERROR source=server.go:807 msg="post predict" error="Post \"http://127.0.0.1:42821/completion\": context canceled" [GIN] 2025/08/08 - 02:15:49 | 200 | 2.272718522s | 172.17.0.1 | POST "/api/generate" [GIN] 2025/08/08 - 02:15:49 | 404 | 820.049µs | 172.17.0.1 | POST "/api/generate" time=2025-08-08T02:15:49.657Z level=ERROR source=server.go:807 msg="post predict" error="Post \"http://127.0.0.1:42821/completion\": context canceled" [GIN] 2025/08/08 - 02:15:49 | 200 | 606.929414ms | 172.17.0.1 | POST "/api/generate" [GIN] 2025/08/08 - 02:15:52 | 404 | 783.625µs | 172.17.0.1 | POST "/api/generate" time=2025-08-08T02:15:53.306Z level=ERROR source=server.go:807 msg="post predict" error="Post \"http://127.0.0.1:42821/completion\": context canceled" [GIN] 2025/08/08 - 02:15:53 | 200 | 3.622453821s | 172.17.0.1 | POST "/api/generate" [GIN] 2025/08/08 - 02:15:53 | 200 | 101.029513ms | 172.17.0.1 | POST "/api/show" [GIN] 2025/08/08 - 02:15:54 | 200 | 78.520838ms | 172.17.0.1 | POST "/api/show" [GIN] 2025/08/08 - 02:15:55 | 200 | 100.599109ms | 172.17.0.1 | POST "/api/show" [GIN] 2025/08/08 - 02:15:55 | 200 | 99.47526ms | 172.17.0.1 | POST "/api/show" [GIN] 2025/08/08 - 02:15:55 | 200 | 101.515257ms | 172.17.0.1 | POST "/api/show" [GIN] 2025/08/08 - 02:16:40 | 200 | 27.406µs | 127.0.0.1 | HEAD "/" [GIN] 2025/08/08 - 02:16:40 | 200 | 30.508µs | 127.0.0.1 | GET "/api/ps" [GIN] 2025/08/08 - 02:17:05 | 200 | 22.33µs | 127.0.0.1 | HEAD "/" [GIN] 2025/08/08 - 02:17:05 | 200 | 21.118µs | 127.0.0.1 | GET "/api/ps" [GIN] 2025/08/08 - 02:17:47 | 200 | 24.005µs | 127.0.0.1 | HEAD "/" [GIN] 2025/08/08 - 02:17:47 | 200 | 27.324µs | 127.0.0.1 | GET "/api/ps" [GIN] 2025/08/08 - 02:17:48 | 200 | 24.076µs | 127.0.0.1 | HEAD "/" [GIN] 2025/08/08 - 02:17:48 | 200 | 24.453µs | 127.0.0.1 | GET "/api/ps" [GIN] 2025/08/08 - 02:18:36 | 200 | 31.943µs | 127.0.0.1 | HEAD "/" [GIN] 2025/08/08 - 02:18:36 | 200 | 39.346µs | 127.0.0.1 | GET "/api/ps" [GIN] 2025/08/08 - 02:18:37 | 200 | 23.75µs | 127.0.0.1 | HEAD "/" [GIN] 2025/08/08 - 02:18:37 | 200 | 34.403µs | 127.0.0.1 | GET "/api/ps" time=2025-08-08T02:18:39.424Z level=ERROR source=server.go:807 msg="post predict" error="Post \"http://127.0.0.1:42821/completion\": context canceled" time=2025-08-08T02:18:39.424Z level=INFO source=runner.go:646 msg="aborting completion request due to client closing the connection" [GIN] 2025/08/08 - 02:18:39 | 200 | 2m46s | 172.17.0.1 | POST "/api/generate" [GIN] 2025/08/08 - 02:19:15 | 200 | 28.224µs | 172.17.0.1 | GET "/" [GIN] 2025/08/08 - 02:19:15 | 404 | 5.403µs | 172.17.0.1 | GET "/favicon.ico" [GIN] 2025/08/08 - 02:19:37 | 200 | 21.216µs | 127.0.0.1 | HEAD "/" [GIN] 2025/08/08 - 02:19:37 | 200 | 23.773µs | 127.0.0.1 | GET "/api/ps" [GIN] 2025/08/08 - 02:19:37 | 200 | 22.829µs | 127.0.0.1 | HEAD "/" [GIN] 2025/08/08 - 02:19:37 | 200 | 22.603µs | 127.0.0.1 | GET "/api/ps" time=2025-08-08T02:21:19.309Z level=ERROR source=server.go:807 msg="post predict" error="Post \"http://127.0.0.1:42821/completion\": context canceled" time=2025-08-08T02:21:19.309Z level=INFO source=runner.go:646 msg="aborting completion request due to client closing the connection" [GIN] 2025/08/08 - 02:21:19 | 200 | 1m48s | 172.17.0.1 | POST "/api/chat" [GIN] 2025/08/08 - 02:21:42 | 200 | 21.686µs | 127.0.0.1 | HEAD "/" [GIN] 2025/08/08 - 02:21:42 | 200 | 23.775µs | 127.0.0.1 | GET "/api/ps" time=2025-08-08T02:21:48.022Z level=ERROR source=server.go:807 msg="post predict" error="Post \"http://127.0.0.1:42821/completion\": context canceled" time=2025-08-08T02:21:48.022Z level=INFO source=runner.go:646 msg="aborting completion request due to client closing the connection" [GIN] 2025/08/08 - 02:21:48 | 200 | 17.287678521s | 172.17.0.1 | POST "/api/chat" [GIN] 2025/08/08 - 02:23:22 | 200 | 21.187µs | 127.0.0.1 | HEAD "/" [GIN] 2025/08/08 - 02:23:22 | 200 | 1.270011ms | 127.0.0.1 | GET "/api/tags" [GIN] 2025/08/08 - 02:23:32 | 404 | 860.202µs | 172.17.0.1 | POST "/api/generate" [GIN] 2025/08/08 - 02:23:34 | 404 | 874.441µs | 172.17.0.1 | POST "/api/generate" time=2025-08-08T02:23:35.027Z level=ERROR source=server.go:807 msg="post predict" error="Post \"http://127.0.0.1:42821/completion\": context canceled" time=2025-08-08T02:23:35.027Z level=INFO source=runner.go:646 msg="aborting completion request due to client closing the connection" ``` ### Relevant log output ```shell ``` ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_
GiteaMirror added the bug label 2026-04-29 06:07:03 -05:00
GiteaMirror commented 2026-04-29 06:07:09 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Aug 21, 2025):

https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#linux-docker

<!-- gh-comment-id:3209878944 --> @rick-github commented on GitHub (Aug 21, 2025): https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#linux-docker
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#54485
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?