Chang Su 37158f2018 router: Support parallel sampling num > 1 in grpc_server and non-stream handling (#10929)

2025-09-25 20:03:35 -07:00

..

openai

Replace the Kimi-K2 generated tool call idx with history tool call count (#10612)

2025-09-25 18:47:40 -07:00

context.py

Revert "bugfix: Fix output_ids extraction in detokenizer_manager" (#9467)

2025-08-21 17:24:25 -07:00

engine.py

chore: upgrade sgl-kernel 0.3.12 (#10782)

2025-09-23 00:18:54 -07:00

EngineBase.py

Support dynamic LoRA loading / unloading in engine/server API (#7446)

2025-06-27 21:00:27 -07:00

grpc_request_manager.py

router: Support parallel sampling num > 1 in grpc_server and non-stream handling (#10929)

2025-09-25 20:03:35 -07:00

grpc_server.py

router: Support parallel sampling num > 1 in grpc_server and non-stream handling (#10929)

2025-09-25 20:03:35 -07:00

harmony_utils.py

(gpt-oss, oai, chat): Remove Harmony Integration and Implement Native GPT-OSS Tool Call Support (#9043)

2025-08-11 18:59:18 -07:00

http_server_engine.py

[Multimodal][Perf] Use pybase64 instead of base64 (#7724)

2025-07-08 14:00:58 -07:00

http_server.py

[RL] Add destroy process group api (#9979)

2025-09-19 00:31:56 +08:00

tool.py

bugfix for undefined logging functions in HarmonyBrowserTool & HarmonyPythonTool (#9229)

2025-08-25 00:10:35 -07:00