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 14, 05:30 UTC
main
[Feature][P/D]: Optimize NIXL Connector xfer Launch (#23887)
WeiQing Chen committed about 1 year ago
[Attention] Blackwell FP8 MLA support with CUTLASS_MLA backend (#23289)
Matthew Bonanni committed about 1 year ago
Migrate whisper inputs to TensorSchema (#23505)
Benji Beck committed about 1 year ago
[Kernels] Overlap shared experts with send/recv (#23273)
bnellnm committed about 1 year ago
[V1] v1 engine + full CUDA graph support for PLaMo2 (#23998)
nopperl committed about 1 year ago
[Bugfix] Fixing division by zero in triton_attn if query_heads/kv_heads > 16 (#23424)
Burkhard Ringlein committed about 1 year ago
FIX: Add libnuma-dev to Dockerfile for dev stage (#20388)
dongbo910220 committed about 1 year ago
[Model] Remove useless code from MiniMax implementation (#23982)
qscqesze committed about 1 year ago
Support add_generation_prompt in embeddings endpoint with chat request (#23931)
Jakub Smid committed about 1 year ago
[CI] Accelerate mteb test by setting SentenceTransformers mteb score to a constant (#24088)
wang.yuqi committed about 1 year ago
[Misc] Clean up deadcode for legacy processing pipeline (#24153)
Isotr0py committed about 1 year ago
[CI/Build] Serve images used by multimodal tests through local HTTP Server (#23907)
dsinghvi committed about 1 year ago
[Nixl] Heterogeneous TP support FlashInfer (#20189)
Nicolò Lucchesi committed about 1 year ago
[distributed][rl] remove nccl cumem env var override (#24141)
youkaichao committed about 1 year ago
[BugFix] Fix routed_scaling_factor double mul for dots1 and glm4 MoE models (#24132)
Yong Hoon Shin committed about 1 year ago
[Misc] Add check for dual_chunk_attention (#24070)
Jiangyun Zhu committed about 1 year ago
[Doc]: fix typos in Python comments (#24115)
Didier Durand committed about 1 year ago
[Doc]: fix typos in Python comments (#24093)
Didier Durand committed about 1 year ago
[Compile] Fix Compile Warning for `w4a8_mm_entry.cu` (#23660)
Wentao Ye committed about 1 year ago
co63oc committed about 1 year ago