A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 14, 05:30 UTC
[Easy] Fix env type check errors from VLLM_DEBUG_LOG_API_SERVER_RESPONSE (#26742)
Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
Jialin Ouyang committed
Oct 13, 2025 at 18:46 UTC
cfded80793a595ea8bac867b24654c8e0ee26afb
1 file changed
+1
vllm/envs.py
+1
@@ -24,6 +24,7 @@ if TYPE_CHECKING:
24
CUDA_VISIBLE_DEVICES: str | None = None
25
VLLM_ENGINE_ITERATION_TIMEOUT_S: int = 60
26
VLLM_API_KEY: str | None = None
27
+ VLLM_DEBUG_LOG_API_SERVER_RESPONSE: bool = False
28
S3_ACCESS_KEY_ID: str | None = None
29
S3_SECRET_ACCESS_KEY: str | None = None
30
S3_ENDPOINT_URL: str | None = None