Skip to content

GitLab

Unverified Commit 54cf1cae authored by Woosuk Kwon's avatar Woosuk Kwon Committed by GitHub
Browse files

[Misc] Do not print async output warning for v1 (#21151) 


Signed-off-by: default avatarWoosuk Kwon <woosuk.kwon@berkeley.edu>
parent 5780121c
Hide whitespace changes
Inline Side-by-side
Showing with 2 additions and 2 deletions
vllm/platforms/cuda.py
View file @ 54cf1cae
...@@ -99,7 +99,7 @@ class CudaPlatformBase(Platform): ...@@ -99,7 +99,7 @@ class CudaPlatformBase(Platform):
@classmethod @classmethod
def is_async_output_supported(cls, enforce_eager: Optional[bool]) -> bool: def is_async_output_supported(cls, enforce_eager: Optional[bool]) -> bool:
if enforce_eager: if enforce_eager and not envs.VLLM_USE_V1:
logger.warning( logger.warning(
"To see benefits of async output processing, enable CUDA " "To see benefits of async output processing, enable CUDA "
"graph. Since, enforce-eager is enabled, async output " "graph. Since, enforce-eager is enabled, async output "
......
vllm/platforms/rocm.py
View file @ 54cf1cae
...@@ -299,7 +299,7 @@ class RocmPlatform(Platform): ...@@ -299,7 +299,7 @@ class RocmPlatform(Platform):
@classmethod @classmethod
def is_async_output_supported(cls, enforce_eager: Optional[bool]) -> bool: def is_async_output_supported(cls, enforce_eager: Optional[bool]) -> bool:
if enforce_eager: if enforce_eager and not envs.VLLM_USE_V1:
logger.warning( logger.warning(
"To see benefits of async output processing, enable CUDA " "To see benefits of async output processing, enable CUDA "
"graph. Since, enforce-eager is enabled, async output " "graph. Since, enforce-eager is enabled, async output "
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment