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, 05:00 UTC
main
[CI] Write bake config to temp directory instead of repo root (#34569)
Amr Mahdi committed 9 months ago
[Bugfix] Add method to swap quant_method on FusedMoE to fix LoRA issues (#34453)
bnellnm committed 9 months ago
[BugFix] Fix Python 3.13 FlashMLA import error (#34548)
Lucas Wilkinson committed 9 months ago
[Doc] Add Mistral-7b-v0.3 model to the batch invariance validated model (#34584)
Parth Bansal committed 9 months ago
[CI][Frontend] Return 422 instead of 500 for invalid Anthropic tool_choice (#34590)
Andreas Karatzas committed 9 months ago
[CI/Build] Enable tests for recent day-0 new models (#34585)
Isotr0py committed 9 months ago
[torch.compile] Disable ar-rms fusion for ds3-fp4 & DP, fix CI test (#34392)
Luka Govedič committed 9 months ago
[CPU][ARM] Add ARM BF16 cross-compilation support and improve documen… (#33079)
Maryam Tahhan committed 9 months ago
[MM Encoder] Add Triton ViT attention backend (#32183)
Isotr0py committed 9 months ago
[Doc] Update Encoder-Decoder models support doc with Florence-2 (#34581)
Isotr0py committed 9 months ago
Seiji Eicher committed 9 months ago
[Bugfix] Handle num_expert_group=None in flashinfer block-scale FP8 MoE (#34494)
haosdent committed 9 months ago
[BUGFIX] Fix accuracy regression for NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4 with TP>1 (#34476)
Vadim Gimpelson committed 9 months ago
Stanislav Kirillov committed 9 months ago
[CI][Entrypoints] Validate detokenize token IDs to prevent int64 overflow causing 500 (#34468)
Andreas Karatzas committed 9 months ago
[Kernels] Fix Helion GPU utils to use platform-agnostic device name API (#34537)
Andreas Karatzas committed 9 months ago
[Model Runner V2] Minor cleanup for Sampler (#34563)
Woosuk Kwon committed 9 months ago
[Hybrid] Enable mamba prefix cache "align" mode with async scheduling (#33997)
Thomas Parnell committed 9 months ago
[Renderer] Move InputPreprocessor into Renderer (1/2) (#34510)
Cyrus Leung committed 9 months ago
[ROCm][CI] Guard sparse MLA backend imports for ROCm compatibility in tests (#34538)
Andreas Karatzas committed 9 months ago