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
[Docs] Update instructions for how to using existing torch binary (#24892)
Richard Zou committed about 1 year ago
[Metrics] Hide deprecated metrics with gpu_ prefix (#24245)
Mark McLoughlin committed about 1 year ago
[CI] Small Accuracy Eval Test for Deepseek Model (#24259)
Wentao Ye committed about 1 year ago
[Bug] Fix `is_flashmla_supported` Check Error (#24774)
Wentao Ye committed about 1 year ago
Add pytest-cov and .coveragerc (#24778)
Reza Barazesh committed about 1 year ago
[ROCm][Bugfix] Fix the case where there's bias (#24895)
Gregory Shtrasberg committed about 1 year ago
[Deprecation] Remove DeepGEMM Old Symbol Wrapper (#24902)
Wentao Ye committed about 1 year ago
Updated CODEOWNERS for flashinfer, mla, fused_moe (#24906)
Michael Goin committed about 1 year ago
`HuggingFace` -> `Hugging Face` in `Integration with Hugging Face` docs (#24889)
Sergio Paniego Blanco committed about 1 year ago
[Compile] Fix noop_elimination pass and add tests for noop_elimination (#24880)
Jiangyun Zhu committed about 1 year ago
[Tests] fix initialization of kv hash in tests (#24273)
Mickaël Seznec committed about 1 year ago
[ci] fix wheel names for arm wheels (#24898)
Simon Mo committed about 1 year ago
[Bug] Fix Cutlass Scaled MM Compilation Error (#24887)
Wentao Ye committed about 1 year ago
[Performance] Remove redundant clone() calls in cutlass_mla (#24891)
Alexander Matveev committed about 1 year ago
[gpt-oss][1a] create_responses stream outputs BaseModel type, api server is SSE still (#24759)
Andrew Xia committed about 1 year ago
[gpt-oss] Add IncompleteDetails to ResponsesRepsonse (#24561)
Andrew Xia committed about 1 year ago
Bump Flashinfer to 0.3.1 (#24868)
Benjamin Bartels committed about 1 year ago
Update num_tokens_across_dp to use nccl instead of gloo (#24105)
Sage Moore committed about 1 year ago
[Transform] Deterministic Hadacore Transforms (#24106)
Kyle Sayers committed about 1 year ago
Move `MultiModalConfig` from `config/__init__.py` to `config/multimodal.py` (#24659)
Harry Mellor committed about 1 year ago