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 12, 01:00 UTC
main
[P/D] Introduce Mooncake Transfer Engine as kv_connector (#24718)
dtc committed 11 months ago
rasmith committed 11 months ago
[Core] Remove forced None assignment for deprecated PassConfig flags (#29994)
Arpit Khandelwal committed 11 months ago
Add DeepSeek-V3.2 tool parser. (#29848)
Xu Wenqing committed 11 months ago
[ROCm] add fallback for aiter fp8 decode mla (#30005)
Ye (Charlotte) Qi committed 11 months ago
[Core] Fix standalone runs of test_reset_prefix_cache_e2e (#29899)
Mark McLoughlin committed 11 months ago
[Misc] Move functions into `PoolingMetadata` (#30027)
Cyrus Leung committed 11 months ago
[CI][AMD] Match Main CI Behavior By Skipping test_eplb_spec_decode In AMD CI (#30006)
Micah Williamson committed 11 months ago
[ROCm] [Bugfix] `compute_attn_mask_seqlen` for qwen3 omni (#29974)
TJian committed 11 months ago
[Rocm][CI] Fix test_speculator_eagle3 by skipping the CompressedTensorw4a16 Model (#30001)
Charlie Fu committed 11 months ago
[docs] Remove _total from counter metrics names (#30028)
CYJiang committed 11 months ago
[Frontend] refactor harmony utils output message parsing (#29820)
daniel-salib committed 11 months ago
[Bugfix] fixed deepseekv32 tool calling error (#30025)
Chauncey committed 11 months ago
[Misc] Various cleanups for MM input processing (#29970)
Cyrus Leung committed 11 months ago
Fix error while downloading dependencies for CPU backend (#29797)
Jianwei Mao committed 11 months ago
[KVConnector] remove unused code (the model aware kv ops class) (#29709)
Kuntai Du committed 11 months ago
Benjamin Bartels committed 11 months ago
[Bugfix][CPU] Fix CPU KV cache fallback memory allocation (#29604)
gausah01 committed 11 months ago
[Bugfix] Fix adapter_enabled IMA (#29977)
Jee Jee Li committed 11 months ago
[Misc] Add docker build env for Ascend NPU (#30015)
Li Wang committed 11 months ago