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 13, 18:15 UTC
main
[Graph Partition][Cache] Use inductor partition ops config (#27702)
Boyuan Feng committed about 1 year ago
Bugfix: Cutlass FP8 FusedMoE bad scaling factors (#27255)
amirkl94 committed about 1 year ago
Eric Yue committed about 1 year ago
[Misc] fix import error for DeepSeekR1ReasoningParser (#28114)
Chauncey committed about 1 year ago
[Hybrid allocator + kv connector] revert connector test changes related to hybrid allocator (#28011)
Kuntai Du committed about 1 year ago
[bugfix] fix wrong `dcp_local_seq_lens` calc (#27518)
Qiu committed about 1 year ago
[Refactor] to simplify and extract the shared logic between chat completion and responses (#27961)
Chauncey committed about 1 year ago
[Refactor] Lazy-loaded reasoning_parser (#28092)
Chauncey committed about 1 year ago
[Model, Core] Support Granite Speech & LoRA for STT (#24455)
Alex Brooks committed about 1 year ago
[BugFix] Fix DCP Assert (AssertionError: DCP not support reorder_batch_threshold > 1 now.) (#28100)
Lucas Wilkinson committed about 1 year ago
[Bugfix] Fix encoder-only model support for transformers backend (#28021)
Isotr0py committed about 1 year ago
[V0 deprecation] Remove VLLM_USE_V1 usage in most modules (#27955)
wangxiyuan committed about 1 year ago
[CI/Build] Enable some fixed tests in AMD CI (#28078)
Zhewen Li committed about 1 year ago
[XPU] Add gpt-oss model support for Intel GPU (#27786)
Kunshang Ji committed about 1 year ago
[Qwen3-Next] MOE configs for A100-SXM4-80GB TP4 TP8 (#27740)
tou committed about 1 year ago
Revert "[PERF] Decouple projections from GDN custom op" (#28080)
Vadim Gimpelson committed about 1 year ago
[ROCm] gemm_a16w16 upstreaming (#26969)
Aleksandr Malyshev committed about 1 year ago
[Multimodal] Make MediaConnector extensible. (#27759)
Chenheli Hua committed about 1 year ago
Added disable rule to track files under benchmarks/lib (#28048)
nadavkluger committed about 1 year ago
[ROCm][Perf] New design on ROCm AITER MHA backend Implementation (#25763)
Pleaplusone committed about 1 year ago