ERROR:apps.litellm.main:Failed to start subprocess: [Errno 12] Cannot allocate memory
ERROR:asyncio:Task exception was never retrieved
future: <Task finished name='Task-3' coro=<start_litellm_background() done, defined at /app/backend/apps/litellm/main.py:98> exception=OSError(12, 'Cannot allocate memory')>
Traceback (most recent call last):
File "/app/backend/apps/litellm/main.py", line 113, in start_litellm_background
await run_background_process(command)
File "/app/backend/apps/litellm/main.py", line 74, in run_background_process
process = await asyncio.create_subprocess_exec(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/asyncio/subprocess.py", line 223, in create_subprocess_exec
transport, protocol = await loop.subprocess_exec(
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "uvloop/loop.pyx", line 2820, in subprocess_exec
File "uvloop/loop.pyx", line 2778, in __subprocess_run
File "uvloop/handles/process.pyx", line 611, in uvloop.loop.UVProcessTransport.new
File "uvloop/handles/process.pyx", line 112, in uvloop.loop.UVProcess._init
OSError: [Errno 12] Cannot allocate memory
Originally created by @imkebe on GitHub (Apr 25, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/1750
# Bug Report
## Description
**Bug Summary:**
Frontend seems to fail because of the `/itellm/api/v1/models` timeout.
**Steps to Reproduce:**
Updated to v0.1.121
**Expected Behavior:**
There shouldn't be any hard LiteLLM deps.
**Actual Behavior:**
After login page the screen is empty. Pending llm models api fetch, while the service has never started.
## Environment
- **Open WebUI Version:**
0.1.121
- **Ollama (if applicable):**
0.1.30, 0.1.32
- **Browser (if applicable):**
Brave 1.65.114 Chromium: 124.0.6367.60 , Firefox 125.0.2
## Reproduction Details
```INFO:apps.litellm.main:Executing command: ['litellm', '--port', '14365', '--host', '127.0.0.1', '--telemetry', 'False', '--config', '/app/backend/data/litellm/config.yaml']
ERROR:apps.litellm.main:Failed to start subprocess: [Errno 12] Cannot allocate memory
ERROR:asyncio:Task exception was never retrieved
future: <Task finished name='Task-3' coro=<start_litellm_background() done, defined at /app/backend/apps/litellm/main.py:98> exception=OSError(12, 'Cannot allocate memory')>
Traceback (most recent call last):
File "/app/backend/apps/litellm/main.py", line 113, in start_litellm_background
await run_background_process(command)
File "/app/backend/apps/litellm/main.py", line 74, in run_background_process
process = await asyncio.create_subprocess_exec(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/asyncio/subprocess.py", line 223, in create_subprocess_exec
transport, protocol = await loop.subprocess_exec(
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "uvloop/loop.pyx", line 2820, in subprocess_exec
File "uvloop/loop.pyx", line 2778, in __subprocess_run
File "uvloop/handles/process.pyx", line 611, in uvloop.loop.UVProcessTransport.new
File "uvloop/handles/process.pyx", line 112, in uvloop.loop.UVProcess._init
OSError: [Errno 12] Cannot allocate memory
```
Why this is an enhancement and no bug related? That was working fine with 0.1.120.
<!-- gh-comment-id:2079250786 -->
@imkebe commented on GitHub (Apr 26, 2024):
Why this is an enhancement and no bug related? That was working fine with 0.1.120.
Also I noticed that the issue is in fact not having a timeout. When I block the URI of that endpoint in browser the Frontend is rendering. So in fact it waits forever trying to fetch the data and blocks the rendering of the Frontend.
<!-- gh-comment-id:2079254183 -->
@imkebe commented on GitHub (Apr 26, 2024):
Also I noticed that the issue is in fact not having a timeout. When I block the URI of that endpoint in browser the Frontend is rendering. So in fact it waits forever trying to fetch the data and blocks the rendering of the Frontend.
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Originally created by @imkebe on GitHub (Apr 25, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/1750
Bug Report
Description
Bug Summary:
Frontend seems to fail because of the
/itellm/api/v1/modelstimeout.Steps to Reproduce:
Updated to v0.1.121
Expected Behavior:
There shouldn't be any hard LiteLLM deps.
Actual Behavior:
After login page the screen is empty. Pending llm models api fetch, while the service has never started.
Environment
Open WebUI Version:
0.1.121
Ollama (if applicable):
0.1.30, 0.1.32
Browser (if applicable):
Brave 1.65.114 Chromium: 124.0.6367.60 , Firefox 125.0.2
Reproduction Details
@imkebe commented on GitHub (Apr 26, 2024):
Why this is an enhancement and no bug related? That was working fine with 0.1.120.
@imkebe commented on GitHub (Apr 26, 2024):
Also I noticed that the issue is in fact not having a timeout. When I block the URI of that endpoint in browser the Frontend is rendering. So in fact it waits forever trying to fetch the data and blocks the rendering of the Frontend.