mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-10-27 10:30:34 +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
@@ -141,7 +141,6 @@ class OpenAIServingChat:
|
||||
previous_num_tokens = 0
|
||||
num_prompt_tokens = 0
|
||||
num_choices = 1
|
||||
tool_called = False
|
||||
max_streaming_response_tokens = (
|
||||
request.max_streaming_response_tokens
|
||||
if request.max_streaming_response_tokens is not None
|
||||
@@ -246,28 +245,20 @@ class OpenAIServingChat:
|
||||
output = res["outputs"]
|
||||
delta_text = output["text"]
|
||||
output_top_logprobs = output["top_logprobs"]
|
||||
previous_num_tokens += len(output["token_ids"])
|
||||
logprobs_res: Optional[LogProbs] = None
|
||||
if request.logprobs and output_top_logprobs is not None:
|
||||
logprobs_res = self._create_chat_logprobs(
|
||||
output_top_logprobs, request.logprobs, request.top_logprobs
|
||||
)
|
||||
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 = tool_delta_message
|
||||
delta_message.reasoning_content = output.get("reasoning_content")
|
||||
if delta_message.tool_calls:
|
||||
tool_called = True
|
||||
else:
|
||||
delta_message = DeltaMessage(
|
||||
content=delta_text,
|
||||
reasoning_content=output.get("reasoning_content"),
|
||||
prompt_token_ids=None,
|
||||
completion_token_ids=None,
|
||||
tool_calls=None,
|
||||
)
|
||||
|
||||
previous_num_tokens += len(output["token_ids"])
|
||||
delta_message = DeltaMessage(
|
||||
content=delta_text,
|
||||
reasoning_content=output.get("reasoning_content"),
|
||||
prompt_token_ids=None,
|
||||
completion_token_ids=None,
|
||||
tool_calls=output.get("tool_call_content", []),
|
||||
)
|
||||
|
||||
choice = ChatCompletionResponseStreamChoice(
|
||||
index=0,
|
||||
@@ -285,7 +276,10 @@ class OpenAIServingChat:
|
||||
max_tokens = request.max_completion_tokens or request.max_tokens
|
||||
if has_no_token_limit or previous_num_tokens != max_tokens:
|
||||
choice.finish_reason = "stop"
|
||||
if tool_called:
|
||||
if (
|
||||
self.engine_client.reasoning_parser == "ernie_x1"
|
||||
and output.get("finish_reason", "") == "tool_calls"
|
||||
):
|
||||
choice.finish_reason = "tool_calls"
|
||||
else:
|
||||
choice.finish_reason = "length"
|
||||
@@ -425,7 +419,7 @@ class OpenAIServingChat:
|
||||
role="assistant",
|
||||
content=output["text"],
|
||||
reasoning_content=output.get("reasoning_content"),
|
||||
tool_calls=output.get("tool_call"),
|
||||
tool_calls=output.get("tool_call_content"),
|
||||
prompt_token_ids=prompt_token_ids if request.return_token_ids else None,
|
||||
completion_token_ids=completion_token_ids if request.return_token_ids else None,
|
||||
text_after_process=text_after_process if request.return_token_ids else None,
|
||||
@@ -445,7 +439,7 @@ class OpenAIServingChat:
|
||||
max_tokens = request.max_completion_tokens or request.max_tokens
|
||||
if has_no_token_limit or previous_num_tokens != max_tokens:
|
||||
choice.finish_reason = "stop"
|
||||
if output.get("tool_call"):
|
||||
if self.engine_client.reasoning_parser == "ernie_x1" and output.get("finish_reason", "") == "tool_calls":
|
||||
choice.finish_reason = "tool_calls"
|
||||
else:
|
||||
choice.finish_reason = "length"
|
||||
|
||||
Reference in New Issue
Block a user