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 9, 17:06 UTC
main
fix: Add glm4_moe_lite to MLA detection (#32614)
Markus / Mark committed 10 months ago
[cudagraphs] Refactor cudagraph capture loop (#32946)
Lucas Wilkinson committed 10 months ago
[Model Runner V2] Add KV Connector support (#32742)
Nick Hill committed 10 months ago
[Bugfix][CI] Fix pre-commit (#32956)
Matthew Bonanni committed 10 months ago
[CI][torch nightlies] Use main Dockerfile with flags for nightly torch tests (#30443)
Orion Reblitz-Richardson committed 10 months ago
[V1][Hybrid] Mamba Prefix Caching with align mode (#30877)
Harry Huang committed 10 months ago
[Model] Enable LoRA support for internvl2 (#32397)
Matteo Fari committed 10 months ago
[torch.compile][CI] Add back attn fusion on hopper/ada (#32940)
Luka Govedič committed 10 months ago
[Frontend] add logprob, compression_rate to 'verbose_json' features (#31059)
sangbumlikeagod committed 10 months ago
[Hardware][AMD][CI][Bugfix] Fix Kernels Attention Cache test (#32904)
Matt committed 10 months ago
[ROCm][PD] Remove unused moriio connector proxy code (#32939)
Mark McLoughlin committed 10 months ago
[Bugfix] Fix FP8 MoE EP Weight Loading for ModelOpt Llama4 (#32886)
baonudesifeizhai committed 10 months ago
[Misc] Postpone torch_profiler deprecation (#32867)
Nicolò Lucchesi committed 10 months ago
[Bugfix] Disable tma_aligned_scales in test_fusions_e2e (#32916)
Xin Yang committed 10 months ago
[Bugfix] Fix getting vision features in Transformer Multimodal backend (#32933)
Raushan Turganbay committed 10 months ago
[Feature]: Remove DtoH Copy for lfm2_vl On Default Stream (#32815)
tianshu-Michael-yu committed 10 months ago
[CPU][Feat] Update PyTorch to v2.10 for CPU Backend (#32869)
Fadi Arafeh committed 10 months ago
[Benchmark][Bugfix] Fix race condtion when starting server for sweep benchmark (#32927)
Isotr0py committed 10 months ago
[CPU Backend][BugFix] Fix failing CPU MoE test (#32876)
Fadi Arafeh committed 10 months ago
wang.yuqi committed 10 months ago