xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-01-19 17:54:39 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Bug] Fix env string "0" same to True (#28159)

Browse Source 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
This commit is contained in:
Wentao Ye 2025-11-05 20:04:20 -05:00 committed by GitHub
parent d79d9f0780
commit 90189c71a9
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 6 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
vllm/envs.py
View File

@ -776,7 +776,7 @@ environment_variables: dict[str, Callable[[], Any]] = {
# If set, the OpenAI API server will stay alive even after the underlying
# AsyncLLMEngine errors and stops serving requests
"VLLM_KEEP_ALIVE_ON_ENGINE_DEATH": lambda: bool(
os.getenv("VLLM_KEEP_ALIVE_ON_ENGINE_DEATH", 0)
int(os.getenv("VLLM_KEEP_ALIVE_ON_ENGINE_DEATH", "0"))
),
# If the env var VLLM_ALLOW_LONG_MAX_MODEL_LEN is set, it allows
# the user to specify a max sequence length greater than
@ -1313,7 +1313,9 @@ environment_variables: dict[str, Callable[[], Any]] = {
),
# If set, it means we pre-downloaded cubin files and flashinfer will
# read the cubin files directly.
"VLLM_HAS_FLASHINFER_CUBIN": lambda: os.getenv("VLLM_HAS_FLASHINFER_CUBIN", False),
"VLLM_HAS_FLASHINFER_CUBIN": lambda: bool(
int(os.getenv("VLLM_HAS_FLASHINFER_CUBIN", "0"))
),
# Supported options:
# - "flashinfer-cudnn": use flashinfer cudnn GEMM backend
# - "flashinfer-trtllm": use flashinfer trtllm GEMM backend
@ -1449,8 +1451,8 @@ environment_variables: dict[str, Callable[[], Any]] = {
# top 5 collected objects
"VLLM_GC_DEBUG": lambda: os.getenv("VLLM_GC_DEBUG", ""),
# Disables parallel execution of shared_experts via separate cuda stream
"VLLM_DISABLE_SHARED_EXPERTS_STREAM": lambda: os.getenv(
"VLLM_DISABLE_SHARED_EXPERTS_STREAM", False
"VLLM_DISABLE_SHARED_EXPERTS_STREAM": lambda: bool(
int(os.getenv("VLLM_DISABLE_SHARED_EXPERTS_STREAM", "0"))
),
# Format for saving torch.compile cache artifacts
# - "binary": saves as binary file