Yingchun Lai a5bbcda968 fix: prefer to use max_completion_tokens rather than max_tokens (#17516)

2026-01-21 20:22:20 -08:00

..

ollama

Add Ollama-compatible API endpoints + Smart Router (#14376)

2025-12-16 20:43:38 -08:00

openai

fix: prefer to use max_completion_tokens rather than max_tokens (#17516)

2026-01-21 20:22:20 -08:00

context.py

Fix condition for streaming output_ids in tokenizer manager (#13759)

2025-11-29 13:56:15 -08:00

engine.py

Update flashinfer to 0.6.1 (#15551)

2026-01-17 00:48:30 +08:00

EngineBase.py

feat(engine): add rid parameter to methods in Engine class (#13095)

2025-11-11 22:37:54 -08:00

grpc_server.py

[gRPC] Add GetLoads RPC for comprehensive load metrics (#17087)

2026-01-14 12:05:10 -08:00

harmony_utils.py

Fix condition for streaming output_ids in tokenizer manager (#13759)

2025-11-29 13:56:15 -08:00

http_server_engine.py

[Lint] Add python/sglang to ruff F401 checks and remove unused imports in files (#11685)

2025-10-17 16:49:46 -07:00

http_server.py

[Auto Sync] Update detokenizer_manager.py, io_struct.py, mu... (20260120) (#17442)

2026-01-21 14:48:32 -08:00

tool.py

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

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

v1_loads.py

[API] Add /v1/loads endpoint for load metrics (#16976)

2026-01-14 09:13:20 -08:00

warmup.py

Clean up imports and move files (#14317)

2025-12-02 16:31:54 -08:00