apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-24 13:28:13 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[feature] support reward api (#4518)
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 
Co-authored-by: SunLei <sunlei5788@gmail.com>
This commit is contained in:
xiaolei373
2025-10-29 00:20:28 +08:00
committed by GitHub
parent a012e3608b
commit 14e7d88ea4
9 changed files with 362 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
fastdeploy/engine/common_engine.py
View File

@@ -886,24 +886,27 @@ class EngineService:
for request_id, contents in results.items():
new_contents = []
for content in contents:
decode_type = content.outputs.decode_type
delta_text = ""
if decode_type == 0:
delta_text, token_ids = self._decode_token(
token_ids=content.outputs.token_ids, req_id=request_id, is_end=content.finished
)
if isinstance(content, RequestOutput):
decode_type = content.outputs.decode_type
delta_text = ""
if decode_type == 0:
delta_text, token_ids = self._decode_token(
token_ids=content.outputs.token_ids, req_id=request_id, is_end=content.finished
)
else:
token_ids = content.outputs.token_ids
if len(token_ids):
content.outputs.token_ids = token_ids
content.outputs.text = delta_text
new_contents.append(content)
elif content.finished:
new_contents.append(content)
else:
llm_logger.warning(
f"current tokens need to accumulate, req_id: {request_id} {content.outputs.token_ids}"
)
else:
token_ids = content.outputs.token_ids
if len(token_ids):
content.outputs.token_ids = token_ids
content.outputs.text = delta_text
new_contents.append(content)
elif content.finished:
new_contents.append(content)
else:
llm_logger.warning(
f"current tokens need to accumulate, req_id: {request_id} {content.outputs.token_ids}"
)
if len(new_contents):
llm_logger.info(f"Send response for request id: {request_id}")
self.send_response_server.send_response(request_id, new_contents)