github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-16 05:05:37 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #2444] Ollama docker container crash full WSL2 Ubuntu #1426

New Issue
Closed
opened 2026-04-12 11:18:12 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 11:18:12 -05:00
Owner
Copy Link

Originally created by @wizd on GitHub (Feb 11, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/2444

Originally assigned to: @dhiltgen on GitHub.

docker container setup as bellow.

version: "3.7"

services:
  ollama:
    container_name: ollama
    image: ollama/ollama:latest
    ports:
      - "5310:11434"
    volumes:
      - ./ollama:/root/.ollama
    restart: unless-stopped
    environment:
      - CUDA_VISIBLE_DEVICES=0,1
      - OLLAMA_ORIGINS=*
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]

  ollama-webui:
    image: ghcr.io/ollama-webui/ollama-webui:main
    container_name: ollama-webui
    ports:
      - "7000:8080"
    volumes:
      - ./ollama-webui1:/app/backend/data
    environment:
      - 'OLLAMA_API_BASE_URL=http://ollama:11434/api'
    restart: unless-stopped

modelfile as bellow:

FROM miqu-1-70b.q2_k.gguf
PARAMETER num_ctx 24000
PARAMETER num_gpu 81

logs:

...
....................................................................................................
llama_new_context_with_model: n_ctx      = 26000
llama_new_context_with_model: freq_base  = 1000000.0
llama_new_context_with_model: freq_scale = 1
llama_kv_cache_init:      CUDA0 KV buffer size =  4164.06 MiB
llama_kv_cache_init:      CUDA1 KV buffer size =  3960.94 MiB
llama_new_context_with_model: KV self size  = 8125.00 MiB, K (f16): 4062.50 MiB, V (f16): 4062.50 MiB
llama_new_context_with_model:  CUDA_Host input buffer size   =    66.88 MiB
llama_new_context_with_model:      CUDA0 compute buffer size =  3683.66 MiB
llama_new_context_with_model:      CUDA1 compute buffer size =  3683.66 MiB
llama_new_context_with_model:  CUDA_Host compute buffer size =    17.60 MiB
llama_new_context_with_model: graph splits (measure): 5
time=2024-02-10T01:16:44.820Z level=INFO source=dyn_ext_server.go:156 msg="Starting llama main loop"
[GIN] 2024/02/10 - 01:16:52 | 200 |  46.01445749s |      172.22.0.1 | POST     "/api/generate"
[GIN] 2024/02/10 - 01:17:02 | 200 |  9.530461175s |      172.22.0.1 | POST     "/api/generate"
[GIN] 2024/02/10 - 01:17:11 | 200 |  9.062014736s |      172.22.0.1 | POST     "/api/generate"
error from daemon in stream: Error grabbing logs: invalid character '\x00' looking for beginning of value

(base) super@dev-local-ai:~/data/ollama$ docker logs -f ollama
[已退出进程，代码为 1 (0x00000001)]
现在可以使用Ctrl+D关闭此终端，或按 Enter 重新启动。
远程主机强迫关闭了一个现有的连接。
Error code: Wsl/Service/0x80072746
Press any key to continue...
Originally created by @wizd on GitHub (Feb 11, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/2444 Originally assigned to: @dhiltgen on GitHub. docker container setup as bellow. ``` version: "3.7" services: ollama: container_name: ollama image: ollama/ollama:latest ports: - "5310:11434" volumes: - ./ollama:/root/.ollama restart: unless-stopped environment: - CUDA_VISIBLE_DEVICES=0,1 - OLLAMA_ORIGINS=* deploy: resources: reservations: devices: - driver: nvidia count: all capabilities: [gpu] ollama-webui: image: ghcr.io/ollama-webui/ollama-webui:main container_name: ollama-webui ports: - "7000:8080" volumes: - ./ollama-webui1:/app/backend/data environment: - 'OLLAMA_API_BASE_URL=http://ollama:11434/api' restart: unless-stopped ``` modelfile as bellow: ``` FROM miqu-1-70b.q2_k.gguf PARAMETER num_ctx 24000 PARAMETER num_gpu 81 ``` logs: ``` ... .................................................................................................... llama_new_context_with_model: n_ctx = 26000 llama_new_context_with_model: freq_base = 1000000.0 llama_new_context_with_model: freq_scale = 1 llama_kv_cache_init: CUDA0 KV buffer size = 4164.06 MiB llama_kv_cache_init: CUDA1 KV buffer size = 3960.94 MiB llama_new_context_with_model: KV self size = 8125.00 MiB, K (f16): 4062.50 MiB, V (f16): 4062.50 MiB llama_new_context_with_model: CUDA_Host input buffer size = 66.88 MiB llama_new_context_with_model: CUDA0 compute buffer size = 3683.66 MiB llama_new_context_with_model: CUDA1 compute buffer size = 3683.66 MiB llama_new_context_with_model: CUDA_Host compute buffer size = 17.60 MiB llama_new_context_with_model: graph splits (measure): 5 time=2024-02-10T01:16:44.820Z level=INFO source=dyn_ext_server.go:156 msg="Starting llama main loop" [GIN] 2024/02/10 - 01:16:52 | 200 | 46.01445749s | 172.22.0.1 | POST "/api/generate" [GIN] 2024/02/10 - 01:17:02 | 200 | 9.530461175s | 172.22.0.1 | POST "/api/generate" [GIN] 2024/02/10 - 01:17:11 | 200 | 9.062014736s | 172.22.0.1 | POST "/api/generate" error from daemon in stream: Error grabbing logs: invalid character '\x00' looking for beginning of value (base) super@dev-local-ai:~/data/ollama$ docker logs -f ollama [已退出进程，代码为 1 (0x00000001)] 现在可以使用Ctrl+D关闭此终端，或按 Enter 重新启动。 远程主机强迫关闭了一个现有的连接。 Error code: Wsl/Service/0x80072746 Press any key to continue... ```
GiteaMirror commented 2026-04-12 11:18:13 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Mar 11, 2024):

This looks like it might be a low-level docker problem, but I'm not sure.

Can you try running the container using docker run -it ... and see if we can see more error reporting?

<!-- gh-comment-id:1989640535 --> @dhiltgen commented on GitHub (Mar 11, 2024): This looks like it might be a low-level docker problem, but I'm not sure. Can you try running the container using `docker run -it ...` and see if we can see more error reporting?
GiteaMirror commented 2026-04-12 11:18:13 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Mar 27, 2024):

If you're still having problems, please share logs from a stand-alone interactive container run.

<!-- gh-comment-id:2023977039 --> @dhiltgen commented on GitHub (Mar 27, 2024): If you're still having problems, please share logs from a stand-alone interactive container run.
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
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#1426
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?