xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-10 02:35:24 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Bugfix] Fix faulty triton importing logic when using Ray for DP (#19734)

Browse Source 
Signed-off-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
Michael Goin 2025-06-18 05:59:29 +09:00 committed by GitHub
parent cda92307c1
commit b447624ee3
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 17 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
vllm/triton_utils/importing.py
View File

@ -1,6 +1,7 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
import os
import types
from importlib.util import find_spec
@ -23,7 +24,22 @@ if HAS_TRITON:
x.driver for x in backends.values()
if x.driver and x.driver.is_active()
]
if len(active_drivers) != 1:
# Check if we're in a distributed environment where CUDA_VISIBLE_DEVICES
# might be temporarily empty (e.g., Ray sets it to "" during actor init)
cuda_visible_devices = os.environ.get("CUDA_VISIBLE_DEVICES")
is_distributed_env = (cuda_visible_devices is not None
and len(cuda_visible_devices.strip()) == 0)
# Apply lenient driver check for distributed environments
if is_distributed_env and len(active_drivers) == 0:
# Allow 0 drivers in distributed environments - they may become
# active later when CUDA context is properly initialized
logger.debug(
"Triton found 0 active drivers in distributed environment. "
"This is expected during initialization.")
elif not is_distributed_env and len(active_drivers) != 1:
# Strict check for non-distributed environments
logger.info(
"Triton is installed but %d active driver(s) found "
"(expected 1). Disabling Triton to prevent runtime errors.",