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, 05:00 UTC
main
[Bugfix] Fix incompatibility between #33372 and #32863 (#33475)
Cyrus Leung committed 9 months ago
[ez] Add structured torch.compile logs (#33213)
Angela Yi committed 9 months ago
[Frontend] Use new Renderer for Completions and Tokenize API (#32863)
Cyrus Leung committed 9 months ago
[perf] v1/spec_decode: skip softmax for all-greedy rejection sampling (#32852)
caozuoba committed 9 months ago
[ROCM] Enable aiter attn backend for qwen3-next model (#32492)
jennyyyyzhen committed 9 months ago
[BugFix] Add synchronize in CutlassW4A8LinearKernel to ensure data is ready for use. (#33078)
Jinwu committed 9 months ago
[Kernel] [Helion] [3/N] Helion kernel registry (#33203)
Yanan Cao committed 9 months ago
Fadi Arafeh committed 9 months ago
Add EAGLE3 support for AFMoE (#33111)
AutumnAurelium committed 9 months ago
Add support for Mistral Large 3 inference with Flashinfer MoE (#33174)
Dimitrios Bariamis committed 9 months ago
[Bugfix] Handle Asym W4A16 (ConchLinearKernel) for CT (#33200)
Matthias Gehre committed 9 months ago
[Bugfix] Fix `Qwen3ASR` language asr tag in output (#33410)
Nicolò Lucchesi committed 9 months ago
[Kernel] [Helion] [2/N] Helion kernel wrapper (#32964)
Yanan Cao committed 9 months ago
[Attention] Clarify comment explaining attn_logits +1 dimension (#33427)
Francesco Fusco committed 9 months ago
[Streaming -> Realtime] Rename all voxtral related classes, fn, files (#33415)
Patrick von Platen committed 9 months ago
[ROCm][CI] Force max_num_seqs=1 on ROCm In test_sharded_state_loader to reduce flakiness (#33277)
Micah Williamson committed 9 months ago
[Misc] offest -> offset in comments and variable names (#33444)
Russell Bryant committed 9 months ago
[BugFix] Fix whisper FA2 + full cudagraphs (#33360)
Lucas Wilkinson committed 9 months ago
[UX] Use gguf `repo_id:quant_type` syntax for examples and docs (#33371)
Michael Goin committed 9 months ago
[Misc] Algin Qwen3-VL-embedding image example outputs with HF repo example (#33419)
Isotr0py committed 9 months ago