mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-10-05 08:37:06 +08:00
Release/2.1 (#3414)
* Pre ce modified (#3335) (#3360) * Pre ce modified (#3335) * update * update * fix * fix * update * update * update * fix * update * update * update * add ut fix pr(3367) * [Bug Fix] Fix V1 video bug (#3387) * fix stopseq error info (#3342) Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com> * [BugFix] Fix default log level of paddleformers (#3377) Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com> * [Polish Code] Remove useless notes * feat(log):add_request_and_response_log (#3392) * Optimize CI execution workflow. (#3371) (#3384) * fix * [BugFix] fix control signal release failed (#3374) * [BugFix] * [BugFix] * [BugFix] * [BugFix] * fix * fix --------- Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com> Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com> * Revert "Merge branch 'feature/online/vs_think_20250813' into release/2.1" This reverts commit02596fc537, reversing changes made to03347626a6. * [XPU] Fixed the issue of performance degradation caused by enabling ENABLE_V1_KVCACHE_SCHEDULER (#3393) * fix v1 schedule oom bug * fix v1 schedule oom bug * [BugFix] fix ErnieProcessor not set raw_prediction (#3401) * [Doc]Release fastdeploy-xpu 2.1.0 (#3407) * fix v1 schedule oom bug * fix v1 schedule oom bug * update release note * [Doc]Release fastdeploy-xpu 2.0.3 (#3408) * fix v1 schedule oom bug * fix v1 schedule oom bug * update release note * update info --------- Co-authored-by: YUNSHEN XIE <1084314248@qq.com> Co-authored-by: ming1753 <61511741+ming1753@users.noreply.github.com> Co-authored-by: JYChen <zoooo0820@qq.com> Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com> Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com> Co-authored-by: Jiang-Jia-Jun <jiangjiajun@baidu.com> Co-authored-by: xiaolei373 <zley373@gmail.com> Co-authored-by: ltd0924 <32387785+ltd0924@users.noreply.github.com> Co-authored-by: yinwei <yinwei_hust@163.com> Co-authored-by: memoryCoderC <1137889088@qq.com>
This commit is contained in:
luukunn
@@ -240,9 +240,9 @@ class OpenAIServingCompletion:
|
||||
dealer.close()
|
||||
self.engine_client.semaphore.release()
|
||||
|
||||
def calc_finish_reason(self, max_tokens, token_num, output, tool_called):
|
||||
def calc_finish_reason(self, max_tokens, token_num, output):
|
||||
if max_tokens is None or token_num != max_tokens:
|
||||
if tool_called or output.get("tool_call"):
|
||||
if self.engine_client.reasoning_parser == "ernie_x1" and output.get("finish_reason", "") == "tool_calls":
|
||||
return "tool_calls"
|
||||
else:
|
||||
return "stop"
|
||||
@@ -271,7 +271,6 @@ class OpenAIServingCompletion:
|
||||
output_tokens = [0] * num_choices
|
||||
inference_start_time = [0] * num_choices
|
||||
first_iteration = [True] * num_choices
|
||||
tool_called = False
|
||||
max_streaming_response_tokens = (
|
||||
request.max_streaming_response_tokens
|
||||
if request.max_streaming_response_tokens is not None
|
||||
@@ -343,41 +342,24 @@ class OpenAIServingCompletion:
|
||||
if request.logprobs and output_top_logprobs is not None:
|
||||
logprobs_res = self._create_completion_logprobs(output_top_logprobs, request.logprobs, 0)
|
||||
|
||||
output_tokens[idx] += 1
|
||||
if self.engine_client.data_processor.tool_parser_obj and not res["finished"]:
|
||||
tool_delta_message = output["tool_delta_message"]
|
||||
if tool_delta_message is None:
|
||||
continue
|
||||
delta_message = CompletionResponseStreamChoice(
|
||||
index=idx,
|
||||
text=output["text"],
|
||||
completion_token_ids=output.get("token_ids") if request.return_token_ids else None,
|
||||
tool_calls=tool_delta_message.tool_calls,
|
||||
reasoning_content=output.get("reasoning_content"),
|
||||
arrival_time=arrival_time,
|
||||
logprobs=logprobs_res,
|
||||
)
|
||||
if tool_delta_message.tool_calls:
|
||||
tool_called = True
|
||||
else:
|
||||
delta_message = CompletionResponseStreamChoice(
|
||||
choices.append(
|
||||
CompletionResponseStreamChoice(
|
||||
index=idx,
|
||||
text=output["text"],
|
||||
prompt_token_ids=None,
|
||||
completion_token_ids=output.get("token_ids") if request.return_token_ids else None,
|
||||
tool_calls=None,
|
||||
raw_prediction=output.get("raw_prediction") if request.return_token_ids else None,
|
||||
tool_calls=output.get("tool_call_content"),
|
||||
reasoning_content=output.get("reasoning_content"),
|
||||
arrival_time=arrival_time,
|
||||
logprobs=logprobs_res,
|
||||
)
|
||||
|
||||
choices.append(delta_message)
|
||||
)
|
||||
output_tokens[idx] += 1
|
||||
|
||||
if res["finished"]:
|
||||
choices[-1].finish_reason = self.calc_finish_reason(
|
||||
request.max_tokens, output_tokens[idx], output, tool_called
|
||||
request.max_tokens, output_tokens[idx], output
|
||||
)
|
||||
send_idx = output.get("send_idx")
|
||||
# 只有当 send_idx 明确为 0 时才记录日志
|
||||
@@ -476,7 +458,7 @@ class OpenAIServingCompletion:
|
||||
token_ids = output["token_ids"]
|
||||
output_text = output["text"]
|
||||
|
||||
finish_reason = self.calc_finish_reason(request.max_tokens, final_res["output_token_ids"], output, False)
|
||||
finish_reason = self.calc_finish_reason(request.max_tokens, final_res["output_token_ids"], output)
|
||||
|
||||
choice_data = CompletionResponseChoice(
|
||||
token_ids=token_ids,
|
||||
@@ -487,7 +469,7 @@ class OpenAIServingCompletion:
|
||||
raw_prediction=output.get("raw_prediction") if request.return_token_ids else None,
|
||||
text_after_process=text_after_process_list[idx] if request.return_token_ids else None,
|
||||
reasoning_content=output.get("reasoning_content"),
|
||||
tool_calls=output.get("tool_call"),
|
||||
tool_calls=output.get("tool_call_content"),
|
||||
logprobs=aggregated_logprobs,
|
||||
finish_reason=finish_reason,
|
||||
)
|
||||
|
||||
Reference in New Issue
Block a user