obscura/vllm
2
0
Fork 0
mirror of https://github.com/vllm-project/vllm.git synced 2026-06-06 00:16:14 +00:00
Code Issues Packages Projects Releases Wiki Activity

[BugFix] Fix hard-coded timeout for multi-API-server startup (#43768)

Browse Source 
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
This commit is contained in:
Vadim Gimpelson
2026-05-28 11:09:13 +04:00
committed by khluu
parent 64e25235c7
commit 799c3afa5d
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
vllm/v1/utils.py
+1 -1
View File
@@ -241,7 +241,7 @@ class APIServerProcessManager:
def gather_actual_addresses(
self,
timeout: float = 60.0,
timeout: float = envs.VLLM_ENGINE_READY_TIMEOUT_S,
) -> tuple[list[str], list[str]]:
"""Return (inputs, outputs) reported by each child, indexed by
``client_index``. Raises ``RuntimeError`` on timeout or premature