biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Frontend] Add --log-error-stack to print stack trace for error response (#22960)

Browse Source 
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
This commit is contained in:
Chen Zhang
2025-08-26 21:58:59 -07:00
committed by GitHub
parent 644d57d531
commit 3210264421
13 changed files with 51 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
vllm/entrypoints/openai/api_server.py
View File

@@ -1749,6 +1749,7 @@ async def init_app_state(
enable_prompt_tokens_details=args.enable_prompt_tokens_details,
enable_force_include_usage=args.enable_force_include_usage,
enable_log_outputs=args.enable_log_outputs,
log_error_stack=args.log_error_stack,
) if "generate" in supported_tasks else None
state.openai_serving_chat = OpenAIServingChat(
engine_client,
@@ -1767,6 +1768,7 @@ async def init_app_state(
enable_prompt_tokens_details=args.enable_prompt_tokens_details,
enable_force_include_usage=args.enable_force_include_usage,
enable_log_outputs=args.enable_log_outputs,
log_error_stack=args.log_error_stack,
) if "generate" in supported_tasks else None
state.openai_serving_completion = OpenAIServingCompletion(
engine_client,
@@ -1776,6 +1778,7 @@ async def init_app_state(
return_tokens_as_token_ids=args.return_tokens_as_token_ids,
enable_prompt_tokens_details=args.enable_prompt_tokens_details,
enable_force_include_usage=args.enable_force_include_usage,
log_error_stack=args.log_error_stack,
) if "generate" in supported_tasks else None
state.openai_serving_pooling = OpenAIServingPooling(
engine_client,
@@ -1784,6 +1787,7 @@ async def init_app_state(
request_logger=request_logger,
chat_template=resolved_chat_template,
chat_template_content_format=args.chat_template_content_format,
log_error_stack=args.log_error_stack,
) if "encode" in supported_tasks else None
state.openai_serving_embedding = OpenAIServingEmbedding(
engine_client,
@@ -1792,12 +1796,14 @@ async def init_app_state(
request_logger=request_logger,
chat_template=resolved_chat_template,
chat_template_content_format=args.chat_template_content_format,
log_error_stack=args.log_error_stack,
) if "embed" in supported_tasks else None
state.openai_serving_classification = ServingClassification(
engine_client,
model_config,
state.openai_serving_models,
request_logger=request_logger,
log_error_stack=args.log_error_stack,
) if "classify" in supported_tasks else None
enable_serving_reranking = ("classify" in supported_tasks and getattr(
@@ -1807,6 +1813,7 @@ async def init_app_state(
model_config,
state.openai_serving_models,
request_logger=request_logger,
log_error_stack=args.log_error_stack,
) if ("embed" in supported_tasks or enable_serving_reranking) else None
state.openai_serving_tokenization = OpenAIServingTokenization(
@@ -1816,18 +1823,21 @@ async def init_app_state(
request_logger=request_logger,
chat_template=resolved_chat_template,
chat_template_content_format=args.chat_template_content_format,
log_error_stack=args.log_error_stack,
)
state.openai_serving_transcription = OpenAIServingTranscription(
engine_client,
model_config,
state.openai_serving_models,
request_logger=request_logger,
log_error_stack=args.log_error_stack,
) if "transcription" in supported_tasks else None
state.openai_serving_translation = OpenAIServingTranslation(
engine_client,
model_config,
state.openai_serving_models,
request_logger=request_logger,
log_error_stack=args.log_error_stack,
) if "transcription" in supported_tasks else None
state.enable_server_load_tracking = args.enable_server_load_tracking