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

feat(log):add_request_and_response_log (#3392)

Browse Source
This commit is contained in:
xiaolei373
2025-08-14 14:50:48 +08:00
committed by GitHub
parent dc5d3ff5a0
commit d1d321bafd
3 changed files with 26 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
fastdeploy/entrypoints/openai/serving_chat.py
View File

@@ -239,6 +239,7 @@ class OpenAIServingChat:
prompt_tokens_details=PromptTokenUsageInfo(cached_tokens=num_cached_tokens),
)
yield f"data: {chunk.model_dump_json(exclude_unset=True)} \n\n"
api_server_logger.info(f"Chat Streaming response send_idx 0: {chunk.model_dump_json()}")
first_iteration = False
output = res["outputs"]
@@ -265,6 +266,7 @@ class OpenAIServingChat:
logprobs=logprobs_res,
arrival_time=arrival_time,
)
if res["finished"]:
num_choices -= 1
work_process_metrics.e2e_request_latency.observe(
@@ -299,6 +301,9 @@ class OpenAIServingChat:
if len(choices) == max_streaming_response_tokens or res["finished"]:
chunk.choices = choices
yield f"data: {chunk.model_dump_json(exclude_unset=True)}\n\n"
# 打印尾包
if res["finished"]:
api_server_logger.info(f"Chat Streaming response last send: {chunk.model_dump_json()}")
choices = []
if choices:
@@ -452,13 +457,15 @@ class OpenAIServingChat:
prompt_tokens_details=PromptTokenUsageInfo(cached_tokens=final_res.get("num_cached_tokens", 0)),
)
work_process_metrics.e2e_request_latency.observe(time.time() - final_res["metrics"]["request_start_time"])
return ChatCompletionResponse(
res = ChatCompletionResponse(
id=request_id,
created=created_time,
model=model_name,
choices=choices,
usage=usage,
)
api_server_logger.info(f"Chat response: {res.model_dump_json()}")
return res
def _create_chat_logprobs(
self,