github-starred/open-webui
2
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2026-07-16 14:39:31 -05:00
Code Issues 2.4k Packages Projects Releases 129 Wiki Activity

[GH-ISSUE #20816] issue: Cancel event sent for long-running tasks, no output retrieved #73900

New Issue
Closed
opened 2026-05-13 06:28:17 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-05-13 06:28:17 -05:00
Owner
Copy Link

Originally created by @moooV252 on GitHub (Jan 20, 2026).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/20816

Check Existing Issues

  • I have searched for any existing and/or related issues.
  • I have searched for any existing and/or related discussions.
  • I have also searched in the CLOSED issues AND CLOSED discussions and found no related items (your issue might already be addressed on the development branch!).
  • I am using the latest version of Open WebUI.

Installation Method

Docker

Open WebUI Version

v0.7.2

Ollama Version (if applicable)

llama.cpp b7779 #6df686b, Ollama latest

Operating System

WSL2 Docker

Browser (if applicable)

No response

Confirmation

  • I have read and followed all instructions in README.md.
  • I am using the latest version of both Open WebUI and Ollama.
  • I have included the Docker container logs.
  • I have provided every relevant configuration, setting, and environment variable used in my setup.
  • I have clearly listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc).
  • I have documented step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation. My steps:
  • Start with the initial platform/version/OS and dependencies used,
  • Specify exact install/launch/configure commands,
  • List URLs visited, user input (incl. example values/emails/passwords if needed),
  • Describe all options and toggles enabled or changed,
  • Include any files or environmental changes,
  • Identify the expected and actual result at each stage,
  • Ensure any reasonably skilled user can follow and hit the same issue.

Expected Behavior

Long running tasks on local external llamacpp with big context window finish and retrieve results.
UPD: tested with ollama, same issue.
UPD2: I've narrowed it down to a port proxy timeout issue in docker -> wsl2 -> windows. Looks like it's not quite related to openwebui, but it would be nice if OW sent keepalive pings to an external endpoint so the connection stays intact. When openwebui is launched in a python venv in windows itself the problem disappears.

Actual Behavior

  1. Openwebui shows that it waits for the result as usual
  2. llamacpp is processing the prompt as usual
    ... long time passes (30min to 2 hours)
  3. llamacpp receives a task cancel request and stops generating when prompt processing is finished and first output tokens should be streamed back to openwebui
  4. openwebui is waiting for the response indefinitely
  5. I manually press the 'cancel' button AFTER checking llamacpp logs which show cancel request event.

I notice this behavior only on long-running tasks, short-running (fast llms, small context windows) work as expected. If the first token gets generated within 1-2 minutes it's ok.

I'm running the latest openwebui image inside WSL2 docker, timeouts are increased both in openwebui using AIOHTTP_CLIENT_TIMEOUT=600000 environment variable as well as --timeout set to the same value in llamacpp launch string.

Made sure to pull the latest image before launching.

Steps to Reproduce

  1. Launch WSL2 under windows.

  2. Run docker openwebui like this:
    docker run -d -p 1414:8080 -v $(pwd)/ow_data:/app/backend/data -e "AIOHTTP_CLIENT_TIMEOUT=600000" --name open-webui ghcr.io/open-webui/open-webui:main

  3. Run llamacpp on another machine, just in plain windows (no wsl, no port forwarding):

llama-server.exe -m D:\llamacpp_models\Qwen3-VL-235B-A22B-Thinking-UD-Q4_K_XL-00001-of-00003.gguf --port 11434 --host 0.0.0.0 --ctx-size 98304 --temp 1.0 --min-p 0.0 --top-p 0.95 --top-k 20 --presence-penalty 0.0 --repeat-penalty 1.05 --jinja --threads 32 -ctk q8_0 -ctv q8_0 -ngl 99 --parallel 1 --timeout 600000 -cram -1 --n-cpu-moe 90 --mmproj d:\llamacpp_models\Qwen3-VL-235B-A22B-mmproj-BF16.gguf

  1. Set up the model in openwebui as an external openai-compatible like http://10.0.0.5:11434/v1
  2. Give it a long-running task for a big context
  3. Openwebui expects output while in reality it sent a cancel request to llamacpp right after the longest part (prompt processing) has been done - as a result it's wasted.

Logs & Screenshots

Docker logs:

....
ab9c7887c515c4ccdd16c6b82ec8159c2b4794319c799546066424c9aba', 'embedding_config': "{'engine': 'ollama', 'model': 'qwen3-embedding:8b-q8_0'}", 'name': '690248463.pdf', 'Content-Type': 'application/pdf', 'file_id': '7b99c1e1-1c98-4802-9057-89c521df987c', 'start_index': 0, 'created_by': '3ae3e9b1-d669-44be-aefc-a34ddc586287'}]]
2026-01-20 09:31:14.104 | INFO     | open_webui.routers.openai:get_all_models:477 - get_all_models()
2026-01-20 09:31:20.694 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52727 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 09:32:21.350 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52735 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 09:33:22.096 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52740 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 09:34:22.807 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52747 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 09:35:23.486 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52752 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 09:36:24.229 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52759 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 09:37:24.929 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52764 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 09:38:25.584 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52771 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 09:39:26.247 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52776 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 09:40:26.889 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52783 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 09:41:27.550 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52788 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 09:42:28.222 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52795 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 09:43:28.917 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52800 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 09:44:29.564 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52808 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 09:45:30.232 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52813 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 09:46:30.912 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52820 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 09:47:31.566 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52825 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 09:48:32.203 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52832 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 09:49:32.847 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52837 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 09:50:33.539 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52847 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 09:51:34.224 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52854 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 09:52:34.968 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52861 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 09:53:35.588 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52866 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 09:54:36.264 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52873 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 09:55:36.930 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52878 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 09:56:37.591 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52885 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 09:57:38.320 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52890 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 09:58:38.720 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52897 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 09:59:39.171 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52902 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 10:00:39.627 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52433 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 10:01:40.157 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52439 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 10:02:40.526 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52446 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 10:03:40.804 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52452 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 10:04:41.129 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52461 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 10:05:41.451 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52470 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 10:06:41.880 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52477 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 10:07:42.429 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52482 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 10:08:42.967 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52489 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 10:09:44.045 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52495 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 10:10:45.036 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52502 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 10:11:45.617 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52507 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 10:12:46.144 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52514 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 10:13:46.787 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52519 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 10:14:47.235 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52526 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 10:15:48.048 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52531 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 10:16:48.587 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52540 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 10:17:49.140 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52545 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 10:18:49.678 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52552 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 10:19:50.317 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52558 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 10:20:50.213 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52565 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 10:21:50.712 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52571 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 10:22:51.170 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52577 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 10:23:51.565 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52583 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 10:24:52.274 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52589 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 10:25:52.668 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52595 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 10:26:53.010 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52600 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 10:27:53.429 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52607 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 10:28:53.852 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52612 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 10:29:54.224 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52620 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 10:30:54.756 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52626 - "GET /_app/version.json HTTP/1.1" 304
2026-01-20 10:30:59.179 | INFO     | open_webui.main:process_chat:1733 - Chat processing was cancelled 
                                               ^ I pressed the cancel button AFTER llamacpp got cancel event

Llamacpp logs:

slot update_slots: id  0 | task 753 | prompt processing progress, n_tokens = 117468, batch.n_tokens = 8, progress = 1.000000
slot update_slots: id  0 | task 753 | prompt done, n_tokens = 117468, batch.n_tokens = 8
slot init_sampler: id  0 | task 753 | init sampler, took 15.27 ms, tokens: text = 103044, total = 117468
srv  log_server_r: request: POST /v1/chat/completions 192.168.10.8 200
srv          stop: cancel task, id_task = 753
slot      release: id  0 | task 753 | stop processing: n_tokens = 117506, truncated = 0
srv  update_slots: all slots are idle

Additional Information

No response

Originally created by @moooV252 on GitHub (Jan 20, 2026). Original GitHub issue: https://github.com/open-webui/open-webui/issues/20816 ### Check Existing Issues - [x] I have searched for any existing and/or related issues. - [x] I have searched for any existing and/or related discussions. - [x] I have also searched in the CLOSED issues AND CLOSED discussions and found no related items (your issue might already be addressed on the development branch!). - [x] I am using the latest version of Open WebUI. ### Installation Method Docker ### Open WebUI Version v0.7.2 ### Ollama Version (if applicable) llama.cpp b7779 #6df686b, Ollama latest ### Operating System WSL2 Docker ### Browser (if applicable) _No response_ ### Confirmation - [x] I have read and followed all instructions in `README.md`. - [x] I am using the latest version of **both** Open WebUI and Ollama. - [x] I have included the Docker container logs. - [x] I have **provided every relevant configuration, setting, and environment variable used in my setup.** - [x] I have clearly **listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup** (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc). - [x] I have documented **step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation**. My steps: - Start with the initial platform/version/OS and dependencies used, - Specify exact install/launch/configure commands, - List URLs visited, user input (incl. example values/emails/passwords if needed), - Describe all options and toggles enabled or changed, - Include any files or environmental changes, - Identify the expected and actual result at each stage, - Ensure any reasonably skilled user can follow and hit the same issue. ### Expected Behavior Long running tasks on local external llamacpp with big context window finish and retrieve results. UPD: tested with ollama, same issue. **UPD2: I've narrowed it down to a port proxy timeout issue in docker -> wsl2 -> windows. Looks like it's not quite related to openwebui, but it would be nice if OW sent keepalive pings to an external endpoint so the connection stays intact.** When openwebui is launched in a python venv in windows itself the problem disappears. ### Actual Behavior 1) Openwebui shows that it waits for the result as usual 2) llamacpp is processing the prompt as usual ... long time passes (30min to 2 hours) 3) llamacpp receives a task cancel request and stops generating when prompt processing is finished and first output tokens should be streamed back to openwebui 4) openwebui is waiting for the response indefinitely 5) I manually press the 'cancel' button AFTER checking llamacpp logs which show cancel request event. I notice this behavior only on long-running tasks, short-running (fast llms, small context windows) work as expected. If the first token gets generated within 1-2 minutes it's ok. I'm running the latest openwebui image inside WSL2 docker, timeouts are increased both in openwebui using AIOHTTP_CLIENT_TIMEOUT=600000 environment variable as well as --timeout set to the same value in llamacpp launch string. Made sure to pull the latest image before launching. ### Steps to Reproduce 1) Launch WSL2 under windows. 2) Run docker openwebui like this: `docker run -d -p 1414:8080 -v $(pwd)/ow_data:/app/backend/data -e "AIOHTTP_CLIENT_TIMEOUT=600000" --name open-webui ghcr.io/open-webui/open-webui:main` 3) Run llamacpp on another machine, just in plain windows (no wsl, no port forwarding): `llama-server.exe -m D:\llamacpp_models\Qwen3-VL-235B-A22B-Thinking-UD-Q4_K_XL-00001-of-00003.gguf --port 11434 --host 0.0.0.0 --ctx-size 98304 --temp 1.0 --min-p 0.0 --top-p 0.95 --top-k 20 --presence-penalty 0.0 --repeat-penalty 1.05 --jinja --threads 32 -ctk q8_0 -ctv q8_0 -ngl 99 --parallel 1 --timeout 600000 -cram -1 --n-cpu-moe 90 --mmproj d:\llamacpp_models\Qwen3-VL-235B-A22B-mmproj-BF16.gguf` 4) Set up the model in openwebui as an external openai-compatible like `http://10.0.0.5:11434/v1` 5) Give it a long-running task for a big context 6) Openwebui expects output while in reality it sent a cancel request to llamacpp right after the longest part (prompt processing) has been done - as a result it's wasted. ### Logs & Screenshots Docker logs: ``` .... ab9c7887c515c4ccdd16c6b82ec8159c2b4794319c799546066424c9aba', 'embedding_config': "{'engine': 'ollama', 'model': 'qwen3-embedding:8b-q8_0'}", 'name': '690248463.pdf', 'Content-Type': 'application/pdf', 'file_id': '7b99c1e1-1c98-4802-9057-89c521df987c', 'start_index': 0, 'created_by': '3ae3e9b1-d669-44be-aefc-a34ddc586287'}]] 2026-01-20 09:31:14.104 | INFO | open_webui.routers.openai:get_all_models:477 - get_all_models() 2026-01-20 09:31:20.694 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52727 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 09:32:21.350 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52735 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 09:33:22.096 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52740 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 09:34:22.807 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52747 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 09:35:23.486 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52752 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 09:36:24.229 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52759 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 09:37:24.929 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52764 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 09:38:25.584 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52771 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 09:39:26.247 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52776 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 09:40:26.889 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52783 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 09:41:27.550 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52788 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 09:42:28.222 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52795 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 09:43:28.917 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52800 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 09:44:29.564 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52808 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 09:45:30.232 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52813 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 09:46:30.912 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52820 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 09:47:31.566 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52825 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 09:48:32.203 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52832 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 09:49:32.847 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52837 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 09:50:33.539 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52847 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 09:51:34.224 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52854 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 09:52:34.968 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52861 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 09:53:35.588 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52866 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 09:54:36.264 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52873 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 09:55:36.930 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52878 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 09:56:37.591 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52885 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 09:57:38.320 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52890 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 09:58:38.720 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52897 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 09:59:39.171 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52902 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 10:00:39.627 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52433 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 10:01:40.157 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52439 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 10:02:40.526 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52446 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 10:03:40.804 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52452 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 10:04:41.129 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52461 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 10:05:41.451 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52470 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 10:06:41.880 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52477 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 10:07:42.429 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52482 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 10:08:42.967 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52489 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 10:09:44.045 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52495 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 10:10:45.036 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52502 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 10:11:45.617 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52507 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 10:12:46.144 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52514 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 10:13:46.787 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52519 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 10:14:47.235 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52526 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 10:15:48.048 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52531 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 10:16:48.587 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52540 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 10:17:49.140 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52545 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 10:18:49.678 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52552 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 10:19:50.317 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52558 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 10:20:50.213 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52565 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 10:21:50.712 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52571 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 10:22:51.170 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52577 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 10:23:51.565 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52583 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 10:24:52.274 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52589 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 10:25:52.668 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52595 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 10:26:53.010 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52600 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 10:27:53.429 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52607 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 10:28:53.852 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52612 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 10:29:54.224 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52620 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 10:30:54.756 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 172.29.160.1:52626 - "GET /_app/version.json HTTP/1.1" 304 2026-01-20 10:30:59.179 | INFO | open_webui.main:process_chat:1733 - Chat processing was cancelled ^ I pressed the cancel button AFTER llamacpp got cancel event ``` Llamacpp logs: ``` slot update_slots: id 0 | task 753 | prompt processing progress, n_tokens = 117468, batch.n_tokens = 8, progress = 1.000000 slot update_slots: id 0 | task 753 | prompt done, n_tokens = 117468, batch.n_tokens = 8 slot init_sampler: id 0 | task 753 | init sampler, took 15.27 ms, tokens: text = 103044, total = 117468 srv log_server_r: request: POST /v1/chat/completions 192.168.10.8 200 srv stop: cancel task, id_task = 753 slot release: id 0 | task 753 | stop processing: n_tokens = 117506, truncated = 0 srv update_slots: all slots are idle ``` ### Additional Information _No response_
GiteaMirror added the bug label 2026-05-13 06:28:17 -05:00
GiteaMirror commented 2026-05-13 06:28:19 -05:00
Author
Owner
Copy Link

@owui-terminator[bot] commented on GitHub (Jan 20, 2026):

🔍 Similar Issues Found

I found some existing issues that might be related to this one. Please check if any of these are duplicates or contain helpful solutions:

  1. #20361 Issue: Large-scale model setting-related functionality fails.
    by shentong0722 • Jan 04, 2026 • bug

💡 Tips:

  • If this is a duplicate, please consider closing this issue and adding any additional details to the existing one
  • If you found a solution in any of these issues, please share it here to help others

This comment was generated automatically by a bot. Please react with a 👍 if this comment was helpful, or a 👎 if it was not.

<!-- gh-comment-id:3772351116 --> @owui-terminator[bot] commented on GitHub (Jan 20, 2026): 🔍 **Similar Issues Found** I found some existing issues that might be related to this one. Please check if any of these are duplicates or contain helpful solutions: 1. [#20361](https://github.com/open-webui/open-webui/issues/20361) **Issue: Large-scale model setting-related functionality fails.** *by shentong0722 • Jan 04, 2026 • `bug`* --- 💡 **Tips:** - If this is a duplicate, please consider closing this issue and adding any additional details to the existing one - If you found a solution in any of these issues, please share it here to help others *This comment was generated automatically by a bot.* Please react with a 👍 if this comment was helpful, or a 👎 if it was not.
GiteaMirror commented 2026-05-13 06:28:19 -05:00
Author
Owner
Copy Link

@tjbck commented on GitHub (Jan 22, 2026):

Open to reviewing PRs.

<!-- gh-comment-id:3783707129 --> @tjbck commented on GitHub (Jan 22, 2026): Open to reviewing PRs.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
confirmed
confirmed issue
core
documentation
enhancement
good first issue
help wanted
non-core
pull-request
Mirrored from GitHub Pull Request
 python
question
testing wanted
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/open-webui#73900
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?