@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 3430857b64
Fork 0

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 16, 07:00 UTC

[Misc] Increase default video fetch timeout (#10495)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>

Cyrus Leung committed Nov 21, 2024 at 15:06 UTC 3430857b641131ffabf215ab569c41696b57b953
1 file changed +1 -1
vllm/envs.py
+1 -1
@@ -49,7 +49,7 @@ if TYPE_CHECKING:
49 VLLM_WORKER_MULTIPROC_METHOD: str = "fork"
50 VLLM_ASSETS_CACHE: str = os.path.join(VLLM_CACHE_ROOT, "assets")
51 VLLM_IMAGE_FETCH_TIMEOUT: int = 5
52 - VLLM_VIDEO_FETCH_TIMEOUT: int = 15
52 + VLLM_VIDEO_FETCH_TIMEOUT: int = 30
53 VLLM_AUDIO_FETCH_TIMEOUT: int = 10
54 VLLM_TARGET_DEVICE: str = "cuda"
55 MAX_JOBS: Optional[str] = None