[Core] Bound draft-token RPC waits by the execute-model timeout (#58779)

Signed-off-by: VS Chandra Mourya <219748331+vschandramourya@users.noreply.github.com>
Co-authored-by: VS Chandra Mourya <219748331+vschandramourya@users.noreply.github.com>
This commit is contained in:
Chandra Mourya
2026-09-26 00:40:22 +00:00
committed by GitHub
co-authored by VS Chandra Mourya
parent fdcce47e9b
commit 8a2364605c
2 changed files with 32 additions and 2 deletions
+3 -1
View File
@@ -369,7 +369,9 @@ class MultiprocExecutor(Executor):
def take_draft_token_ids(self) -> DraftTokenIds | None:
# OPTIMIZATION: Get output only from a single worker (output_rank)
return self.collective_rpc(
"take_draft_token_ids", unique_reply_rank=self.output_rank
"take_draft_token_ids",
unique_reply_rank=self.output_rank,
timeout=envs.VLLM_EXECUTE_MODEL_TIMEOUT_SECONDS,
)
def collective_rpc( # type: ignore[override]