[Frontend] Respect Chat Completion parallel_tool_calls param (#26233)

Signed-off-by: Ben Browning <bbrownin@redhat.com>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>
This commit is contained in:
Ben Browning
2025-11-25 09:56:15 +00:00
committed by GitHub
co-authored by Chauncey
parent a685b47c57
commit e1dd706cd1
6 changed files with 102 additions and 8 deletions
+2 -2
View File
@@ -559,9 +559,9 @@ class ChatCompletionRequest(OpenAIBaseModel):
) = "none"
reasoning_effort: Literal["low", "medium", "high"] | None = None
include_reasoning: bool = True
parallel_tool_calls: bool | None = True
# NOTE this will be ignored by vLLM -- the model determines the behavior
parallel_tool_calls: bool | None = False
# NOTE this will be ignored by vLLM
user: str | None = None
# --8<-- [start:chat-completion-sampling-params]