Support v1/responses and use harmony in serving_chat (#8837)

Signed-off-by: Xinyuan Tong <justinning0323@outlook.com>
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: Xinyuan Tong <justinning0323@outlook.com>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
This commit is contained in:
Chang Su
2025-08-06 16:20:34 -07:00
committed by GitHub
parent cbbd685a46
commit 92cc32d9fc
16 changed files with 2878 additions and 43 deletions

View File

@@ -216,7 +216,7 @@ class DetokenizerManager:
rids=recv_obj.rids,
finished_reasons=recv_obj.finished_reasons,
output_strs=output_strs,
output_ids=None,
output_ids=recv_obj.decode_ids,
prompt_tokens=recv_obj.prompt_tokens,
completion_tokens=recv_obj.completion_tokens,
cached_tokens=recv_obj.cached_tokens,