Skip to content

Fix race condition in LoRA streaming requests #2954

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Lokiiiiii merged 7 commits into from
Nov 19, 2025
Merged

Fix race condition in LoRA streaming requests #2954

Changes from 1 commit
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
6086aea
Fix race condition in streaming responses
Lokiiiiii Nov 19, 2025
1984e7d
Trying a different interface to vllm lora registry
Lokiiiiii Nov 19, 2025
022f0ee
Fixing model name routing for adapter
Lokiiiiii Nov 19, 2025
13dfbf8
removing redundant registration
Lokiiiiii Nov 19, 2025
f979b03
Adding fallback for backwards compatibility
Lokiiiiii Nov 19, 2025
6999ecb
Adding fallback for backwards compatibility
Lokiiiiii Nov 19, 2025
bb5edfc
Reverting backwards compatibility change for fast fail behavior
Lokiiiiii Nov 19, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 3 additions & 12 deletions engines/python/setup/djl_python/lmi_vllm/vllm_async_service.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -239,18 +239,9 @@ async def inference(
return output

if processed_request.lora_request:
original_add_request = self.vllm_engine.add_request

async def add_request_with_lora(*args, **kwargs):
kwargs['lora_request'] = processed_request.lora_request
return await original_add_request(*args, **kwargs)

self.vllm_engine.add_request = add_request_with_lora
try:
response = await processed_request.inference_invoker(
processed_request.vllm_request)
finally:
self.vllm_engine.add_request = original_add_request
response = await processed_request.inference_invoker(
processed_request.vllm_request,
lora_request=processed_request.lora_request)
else:
response = await processed_request.inference_invoker(
processed_request.vllm_request)
Expand Down
Loading