@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / f8fcca100b
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, 03:15 UTC

[Misc] Fix typo for valid_tool_parses (#11753)

Signed-off-by: Rui Qiao <ruisearch42@gmail.com>

Rui Qiao committed Jan 5, 2025 at 23:12 UTC f8fcca100beada88136944976da88f47f363acab
1 file changed +3 -3
vllm/entrypoints/openai/api_server.py
+3 -3
@@ -767,11 +767,11 @@ async def run_server(args, **uvicorn_kwargs) -> None:
767 if args.tool_parser_plugin and len(args.tool_parser_plugin) > 3:
768 ToolParserManager.import_tool_parser(args.tool_parser_plugin)
769
770 - valide_tool_parses = ToolParserManager.tool_parsers.keys()
770 + valid_tool_parses = ToolParserManager.tool_parsers.keys()
771 if args.enable_auto_tool_choice \
772 - and args.tool_call_parser not in valide_tool_parses:
772 + and args.tool_call_parser not in valid_tool_parses:
773 raise KeyError(f"invalid tool call parser: {args.tool_call_parser} "
774 - f"(chose from {{ {','.join(valide_tool_parses)} }})")
774 + f"(chose from {{ {','.join(valid_tool_parses)} }})")
775
776 # workaround to make sure that we bind the port before the engine is set up.
777 # This avoids race conditions with ray.