apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-05 16:48:03 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[Bugfix] fix api server control signal bugs (#3531)
Some checks failed
CE Compile Job / ce_job_pre_check (push) Has been cancelled
Details
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
Details
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
Details
CE Compile Job / Show Code Archive Output (push) Has been cancelled
Details
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
Details
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
Details
CE Compile Job / CE_UPLOAD (push) Has been cancelled
Details
Deploy GitHub Pages / deploy (push) Has been cancelled
Details

Browse Source 
* Update serving_chat.py

* Update serving_completion.py

* Update serving_completion.py
This commit is contained in:
ltd0924
2025-08-25 21:13:04 +08:00
committed by GitHub
parent 2fa173e327
commit 66c5addce4
2 changed files with 11 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
fastdeploy/entrypoints/openai/serving_chat.py
View File

@@ -115,6 +115,7 @@ class OpenAIServingChat:
except Exception as e: except Exception as e:
error_msg = f"request[{request_id}] generator error: {str(e)}, {str(traceback.format_exc())}" error_msg = f"request[{request_id}] generator error: {str(e)}, {str(traceback.format_exc())}"
api_server_logger.error(error_msg) api_server_logger.error(error_msg)
self.engine_client.semaphore.release()
return ErrorResponse(code=400, message=error_msg) return ErrorResponse(code=400, message=error_msg)
del current_req_dict del current_req_dict

6
fastdeploy/entrypoints/openai/serving_completion.py
View File

@@ -127,24 +127,24 @@ class OpenAIServingCompletion:
api_server_logger.error(error_msg) api_server_logger.error(error_msg)
return ErrorResponse(code=408, message=error_msg) return ErrorResponse(code=408, message=error_msg)
try:
try: try:
for idx, prompt in enumerate(request_prompts): for idx, prompt in enumerate(request_prompts):
request_id_idx = f"{request_id}-{idx}" request_id_idx = f"{request_id}-{idx}"
current_req_dict = request.to_dict_for_infer(request_id_idx, prompt) current_req_dict = request.to_dict_for_infer(request_id_idx, prompt)
try:
current_req_dict["arrival_time"] = time.time() current_req_dict["arrival_time"] = time.time()
prompt_token_ids = self.engine_client.format_and_add_data(current_req_dict) prompt_token_ids = self.engine_client.format_and_add_data(current_req_dict)
if isinstance(prompt_token_ids, np.ndarray): if isinstance(prompt_token_ids, np.ndarray):
prompt_token_ids = prompt_token_ids.tolist() prompt_token_ids = prompt_token_ids.tolist()
text_after_process_list.append(current_req_dict.get("text_after_process")) text_after_process_list.append(current_req_dict.get("text_after_process"))
prompt_batched_token_ids.append(prompt_token_ids) prompt_batched_token_ids.append(prompt_token_ids)
del current_req_dict
except Exception as e: except Exception as e:
error_msg = f"OpenAIServingCompletion format error: {e}, {str(traceback.format_exc())}" error_msg = f"OpenAIServingCompletion format error: {e}, {str(traceback.format_exc())}"
api_server_logger.error(error_msg) api_server_logger.error(error_msg)
self.engine_client.semaphore.release()
return ErrorResponse(message=str(e), code=400) return ErrorResponse(message=str(e), code=400)
del current_req_dict
if request.stream: if request.stream:
return self.completion_stream_generator( return self.completion_stream_generator(
request=request, request=request,