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 14, 05:30 UTC
[Bugfix] Add missing enable_log_outputs parameter to init_app_state function (#23634)
Signed-off-by: Matúš Námešný <matus.namesny@ameria.com>
Matúš Námešný committed
Aug 26, 2025 at 14:13 UTC
384dd1b0a899c6761010b42aefe1159c8062f0a4
1 file changed
+2
vllm/entrypoints/openai/api_server.py
+2
@@ -1748,6 +1748,7 @@ async def init_app_state(
1748
reasoning_parser=args.reasoning_parser,
1749
enable_prompt_tokens_details=args.enable_prompt_tokens_details,
1750
enable_force_include_usage=args.enable_force_include_usage,
1751
+ enable_log_outputs=args.enable_log_outputs,
1752
) if "generate" in supported_tasks else None
1753
state.openai_serving_chat = OpenAIServingChat(
1754
engine_client,
@@ -1765,6 +1766,7 @@ async def init_app_state(
1766
reasoning_parser=args.reasoning_parser,
1767
enable_prompt_tokens_details=args.enable_prompt_tokens_details,
1768
enable_force_include_usage=args.enable_force_include_usage,
1769
+ enable_log_outputs=args.enable_log_outputs,
1770
) if "generate" in supported_tasks else None
1771
state.openai_serving_completion = OpenAIServingCompletion(
1772
engine_client,