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

[Misc][Chore] Clean Up AsyncOutputProcessing Logs (#13780)

Browse Source
This commit is contained in:
Robert Shaw
2025-02-24 19:39:07 -05:00
committed by GitHub
parent 1f0ae3ed0a
commit f61528d46d
1 changed files with 0 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
vllm/config.py
View File

@@ -710,8 +710,6 @@ class ModelConfig:
return return
if parallel_config.pipeline_parallel_size > 1: if parallel_config.pipeline_parallel_size > 1:
logger.warning("Async output processing can not be enabled "
"with pipeline parallel")
self.use_async_output_proc = False self.use_async_output_proc = False
return return
@@ -719,15 +717,10 @@ class ModelConfig:
# If the feature combo become valid # If the feature combo become valid
from vllm.platforms import current_platform from vllm.platforms import current_platform
if not current_platform.is_async_output_supported(self.enforce_eager): if not current_platform.is_async_output_supported(self.enforce_eager):
logger.warning(
"Async output processing is not supported on the "
"current platform type %s.", current_platform.device_type)
self.use_async_output_proc = False self.use_async_output_proc = False
return return
if envs.VLLM_USE_RAY_SPMD_WORKER: if envs.VLLM_USE_RAY_SPMD_WORKER:
logger.warning(
"Async output processing can not be enabled with ray spmd")
self.use_async_output_proc = False self.use_async_output_proc = False
return return
@@ -739,8 +732,6 @@ class ModelConfig:
# Reminder: Please update docs/source/features/compatibility_matrix.md # Reminder: Please update docs/source/features/compatibility_matrix.md
# If the feature combo become valid # If the feature combo become valid
if speculative_config: if speculative_config:
logger.warning("Async output processing is not supported with"
" speculative decoding currently.")
self.use_async_output_proc = False self.use_async_output_proc = False
def verify_with_parallel_config( def verify_with_parallel_config(
@@ -768,8 +759,6 @@ class ModelConfig:
"Supported models implement the `SupportsPP` interface.") "Supported models implement the `SupportsPP` interface.")
if self.use_async_output_proc: if self.use_async_output_proc:
logger.warning("Async output processor is not supported with "
"pipeline parallelism currently. Disabling it.")
self.use_async_output_proc = False self.use_async_output_proc = False
def get_hf_config_sliding_window( def get_hf_config_sliding_window(