squall/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[Bugfix] Fix priority in multiprocessing engine (#9277)

Browse Source
This commit is contained in:
Sebastian Schoennenbeck 2024-10-11 17:35:35 +02:00 committed by GitHub
parent 36ea79079b
commit df3dcdf49d
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
vllm/engine/multiprocessing/engine.py
View File

@ -285,7 +285,8 @@ class MQLLMEngine:
params=request.params, params=request.params,
lora_request=request.lora_request, lora_request=request.lora_request,
trace_headers=request.trace_headers, trace_headers=request.trace_headers,
prompt_adapter_request=request.prompt_adapter_request) prompt_adapter_request=request.prompt_adapter_request,
priority=request.priority)
if self.log_requests: if self.log_requests:
logger.info("Added request %s.", request.request_id) logger.info("Added request %s.", request.request_id)