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] Disallow FlashMLA on Blackwell (#24521)
Wentao Ye committed about 1 year ago
[CI] execute all piecewise compilation tests together (#24502)
Jiangyun Zhu committed about 1 year ago
[TPU] Fix tpu structured decoding in mixed batches (#24458)
Chenyaaang committed about 1 year ago
[Docs] Gemma3n `transcriptions` endpoint support (#24512)
Nicolò Lucchesi committed about 1 year ago
[Misc] bump outlines_core to fix the version conflicts with outlines >= 1.2.0 (#24368)
Kazuhiro Serizawa committed about 1 year ago
Extend renderer with embedding support and integrate completion endpoint (#24405)
Flora Feng committed about 1 year ago
[Bugfix] Fix hidden_size for multimodal classification model (#24501)
Jee Jee Li committed about 1 year ago
[ROCm][CI/Build] Sync ROCm dockerfiles with the ROCm fork (#24279)
Gregory Shtrasberg committed about 1 year ago
[Kernels] Add Flash Linear Attention Kernels (#24518)
youkaichao committed about 1 year ago
[Core] Run garbage collector after CUDA graph capture to fix throughput regression (#24128)
Micah Williamson committed about 1 year ago
d.transposed committed about 1 year ago
[Model] Systematic support for fp32 head, pooling models part (#23810)
wang.yuqi committed about 1 year ago
[Compilation][WideEP] Enable Piecewise CUDAGraph for DeepEPHT (#24123)
Wentao Ye committed about 1 year ago
[CI/Build][Doc] Fully deprecate old bench scripts for serving / throughput / latency (#24411)
Ye (Charlotte) Qi committed about 1 year ago
[RL] fast weight update with zmq + ipc handles (#24295)
Weixiao Huang committed about 1 year ago
[gpt-oss] Validate gpt-oss python tool during initialization (#23856)
Chen Zhang committed about 1 year ago
[Misc] Add Codex settings to gitignore (#24493)
Roger Wang committed about 1 year ago
[Misc] Add claude settings to gitignore (#24492)
Ye (Charlotte) Qi committed about 1 year ago
WeiQing Chen committed about 1 year ago
[Doc]: fixing typos to improve docs (#24480)
Didier Durand committed about 1 year ago