A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 8, 01:15 UTC
main
[Frontend] Fix reasoning_tokens for text-based parsers in Responses API (#33513)
Jaeyeon Kim(김재연) committed 9 months ago
Deprecate test-pipeline.yaml (#34864)
Kevin H. Luu committed 9 months ago
[Model Runner V2] Use FP32 for Gumbel Noise (#34854)
Woosuk Kwon committed 9 months ago
[Model Runner V2] Remove unnecessary copies in PW CUDA graph capture (#34849)
Woosuk Kwon committed 9 months ago
rasmith committed 9 months ago
[Model Runner V2] support piecewise & mixed cudagraph (#32771)
zhrrr committed 9 months ago
[MoE Refactor] Convert mxfp4 marlin into modular kernel format (#34588)
Yongye Zhu committed 9 months ago
Fix empty tool_call_id in Anthropic messages API tool result conversion (#34745)
Flora Feng committed 9 months ago
[BUG] Fixing Weight Sync unit test (#34841)
Aaron Hao committed 9 months ago
[Docs] Clean up speculators docs (#34065)
Kyle Sayers committed 9 months ago
[Bugfix] Fix lora tests (#34834)
Cyrus Leung committed 9 months ago
Wenlong Wang committed 9 months ago
rasmith committed 9 months ago
[Model Runner V2] Minor simplification for DCP (#34786)
Woosuk Kwon committed 9 months ago
[Bugfix] Remove assert causing hipErrorStreamCaptureUnsupported (#34455)
Jaden Mathias committed 9 months ago
[Misc] Add mooncake-transfer-engine to kv_connectors requirements (#34826)
Teng Ma committed 9 months ago
[Bugfix] Redo Qwen3.5/Qwen3-Next GDN projector fusion (#34697)
Isotr0py committed 9 months ago
[Bugfix] Fix NVFP4 TRTLLM MoE non-gated support; add gsm8k for Nemotron-3-Nano FP8+NVFP4 (#34725)
Michael Goin committed 9 months ago
[CI][Bugfix] Fix multinode test script (#34820)
Ilya Markov committed 9 months ago
[CI] temporarily disable multi-node tests (#34825)
Robert Shaw committed 9 months ago