[CI] fix docs build failed (#27082)

Chauncey committed about 1 year ago

[Kernel][Performance] Fuse float cast and renormalize to topk softmax kernel (#26717)

zhrrr committed about 1 year ago

[CI/Build] Update compressed tensor test path to fix CPU CI (#27068)

Li, Jiang committed about 1 year ago

[Model] Add support for LightOnOCR (#26916)

Said Taghadouini committed about 1 year ago

[Model] Always use Transformers backend for PaliGemma and Gemma3-MM (#26715)

Cyrus Leung committed about 1 year ago

[CI/Build] Update Llama4 eval yaml (#27070)

Zhewen Li committed about 1 year ago

[Kernel] Lazy import FlashInfer (#26977)

Jee Jee Li committed about 1 year ago

[Bugfix] Fix ReplicatedLinearWithLoRA (#27065)

Jee Jee Li committed about 1 year ago

[Core] Change `execute_model_with_error_logging()` to be a ctx manager (#27060)

Nick Hill committed about 1 year ago

[Bugfix][Qwen] fixes the weights dtype in qwen3_next: it is actually a bfloat16 (#27030)

Tao He committed about 1 year ago

disable graph partition in custom op (#26952)

Boyuan Feng committed about 1 year ago

[Perf] Exploit out-of-band buffers in shm_broadcast (#26961)

Nick Hill committed about 1 year ago

[Docs] Reduce custom syntax used in docs (#27009)

Harry Mellor committed about 1 year ago

vllm bench serve shows num of failed requests (#26478)

Tomas Ruiz committed about 1 year ago

Remove unused imports (#26972)

Lukas Geiger committed about 1 year ago

[torch.compile] fix simple inductor graph partition test (#27050)

Boyuan Feng committed about 1 year ago

[Chore] Separate out `vllm.utils.importlib` (#27022)

Cyrus Leung committed about 1 year ago

[torch.compile] Passing only necessary compilation config to inductor pass config (#27041)

Lucia Fang committed about 1 year ago

[NVIDIA] [Perf] Update to leverage flashinfer trtllm FP4 MOE throughput kernel (#26714)

jiahanc committed about 1 year ago

Refactor Transformers backend to use mixins (#26906)

Harry Mellor committed about 1 year ago