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, 03:45 UTC
main
[Bugfix][MTP][Sparse MLA] Allow sparse MLA with MTP to run with FULL cudagraphs (#34457)
Matthew Bonanni committed 9 months ago
[CI] Fix flaky test_parsable_context (#34717)
Flora Feng committed 9 months ago
[BugFix] Fix sp tests (#34716)
Richard Zou committed 9 months ago
Fixed whisper CPU test that does not spawn properly. (#34324)
almayne committed 9 months ago
[CI][Nixl] Add CrossLayer KV layout tests (#34615)
Nicolò Lucchesi committed 9 months ago
[Renderer] Move InputPreprocessor into Renderer (2/2) (#34560)
Cyrus Leung committed 9 months ago
[CI][BugFix] ShellCheck cleanup to remove baseline and preserve runtime behavior (#34514)
junuxyz committed 9 months ago
Fix docs build warning (#34686)
Harry Mellor committed 9 months ago
[Bugfix] Fix 'remove_instance_endpoint' method logic in disagg_proxy_demo (#32922)
ChenqianCao committed 9 months ago
Remove dead bitsandbytes CxB code from 8-bit inference path (#34633)
Tim Dettmers committed 9 months ago
Revert "[Models] Fuse Qwen3.5 GDN's qkvz_proj and ba_proj" (#34683)
Jiangyun Zhu committed 9 months ago
[Ray] Propagate third-party env vars to Ray workers via prefix matching (#34383)
kourosh hakhamaneshi committed 9 months ago
[CI] Fix bake config artifact path for AMI rebuild pipeline (#34656)
Amr Mahdi committed 9 months ago
[Model Runner V2] Minor refactoring for penalties (#34662)
Woosuk Kwon committed 9 months ago
[Model Runner V2] Minor simplification for BadWordsState (#34669)
Woosuk Kwon committed 9 months ago
[Model Runner V2] Minor cleanup for PP (#34666)
Woosuk Kwon committed 9 months ago
[Model Runner V2] Fix unintended CPU-GPU sync in make_dummy (#34667)
Woosuk Kwon committed 9 months ago
[Bugfix] Fix fused MoE int32 overflow in stride*offset without perf regression (#34507)
haosdent committed 9 months ago
[CI] Enable mypy import following for vllm/v1/kv_offload (#34639)
Aneesh Puttur committed 9 months ago
[Core] Pipeline Parallel support for Model Runner V2 (#33960)
zhanqiuhu committed 9 months ago