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 15, 02:15 UTC
main
[Bugfix] Replace unavailable video url in multimodal test (#20854)
Isotr0py committed over 1 year ago
[Frontend] Abstract prompt and SpeechToTextConfig for transcriptions models (#20637)
Nicolò Lucchesi committed over 1 year ago
[Bugfix] : Fix typo - logger.warn_once -> logger.warning_once (#20852)
Varun Sundar Rabindranath committed over 1 year ago
[CI/Build] Ensure compatability with Transformers v4.53 (#20541)
Isotr0py committed over 1 year ago
[Bugfix] Fix tensor parallel issue in Qwen3 reranker weight loading (#20682)
yurhett committed over 1 year ago
Li, Jiang committed over 1 year ago
[Misc] Restrict deep_gemm's log output (#20827)
Jee Jee Li committed over 1 year ago
Add pynccl all-gatherv and reducescatterv (#20154)
Trevor Morris committed over 1 year ago
Integration SM100 FlashInfer fused allreduce RMSNorm (#20691)
Ilya Markov committed over 1 year ago
Wentao Ye committed over 1 year ago
Update kimi-k2 tool calling docs, enable unit tests (#20821)
bigmoyan committed over 1 year ago
[Bugfix] Fix OOM in language generation test (#20814)
Isotr0py committed over 1 year ago
[Docs] Data Parallel deployment documentation (#20768)
Nick Hill committed over 1 year ago
[Kernel] Basic tuned configs for NVFP4 CUTLASS dense GEMM (#20646)
Michael Goin committed over 1 year ago
[Misc] Add unit tests for MoE ModularKernel combinations + Profiling utility (#20449)
Varun Sundar Rabindranath committed over 1 year ago
[doc] fix ordered list issue (#20819)
Reid committed over 1 year ago
[Bugfix] Add missing field to TritonLanguagePlaceholder (#20812)
Li, Jiang committed over 1 year ago
Temporarily suspend google/gemma-3-1b-it. (#20722)
QiliangCui committed over 1 year ago
[Bugfix] Refactor `/invocations` to be task-agnostic (#20764)
Cyrus Leung committed over 1 year ago
[Core] Add Flashinfer TRTLLM Backend for Flashinfer decode path (SM100). (#19825)
Pavani Majety committed over 1 year ago