biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Misc] Restrict ray version dependency and update PP feature warning in V1 (#15556)

Browse Source
This commit is contained in:
Rui Qiao
2025-03-26 23:21:07 -07:00
committed by GitHub
parent 619d3de8bd
commit df8d3d1287
4 changed files with 8 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
vllm/engine/arg_utils.py
View File

@@ -1686,8 +1686,11 @@ class EngineArgs:
if self.enable_lora and _warn_or_fallback("LORA"):
return False
# PP is supported on V1, but off by default for now.
if self.pipeline_parallel_size > 1 and _warn_or_fallback("PP"):
# PP is supported on V1 with Ray distributed executor,
# but off for MP distributed executor for now.
if (self.pipeline_parallel_size > 1
and self.distributed_executor_backend == "mp"
and _warn_or_fallback("PP (MP distributed executor)")):
return False
# ngram is supported on V1, but off by default for now.