[v1] fix parallel config rank (#13445)

youkaichao committed over 1 year ago

[ROCm] fix get_device_name for rocm (#13438)

Divakar Verma committed over 1 year ago

[Model] Enable quantization support for `transformers` backend (#12960)

Isotr0py committed over 1 year ago

[Misc] Remove dangling references to `SamplingType.BEAM` (#13402)

Harry Mellor committed over 1 year ago

[Bugfix][CI][V1] Work around V1 + CUDA Graph + torch._scaled_mm fallback issue (#13425)

Tyler Michael Smith committed over 1 year ago

[V1][Spec decode] Move drafter to model runner (#13363)

Woosuk Kwon committed over 1 year ago

[V1][PP] Fix intermediate tensor values (#13417)

Cody Yu committed over 1 year ago

[V1] Get input tokens from scheduler (#13339)

Woosuk Kwon committed over 1 year ago

[Bugfix] Fix VLLM_USE_MODELSCOPE issue (#13384)

r.4ntix committed over 1 year ago

[Bugfix] fix xpu communicator (#13368)

Yan Ma committed over 1 year ago

[Model] Support Mamba2 (Codestral Mamba) (#9292)

Tyler Michael Smith committed over 1 year ago

[VLM] Check required fields before initializing field config in `DictEmbeddingItems` (#13380)

Cyrus Leung committed over 1 year ago

[MISC] tiny fixes (#13378)

Mengqing Cao committed over 1 year ago

Run v1 benchmark and integrate with PyTorch OSS benchmark database (#13068)

Huy Do committed over 1 year ago

Fix spelling error in index.md (#13369)

yankooo committed over 1 year ago

[Feature][Spec Decode] Simplify the use of Eagle Spec Decode (#12304)

shangmingc committed over 1 year ago

[V1][Misc] Avoid unnecessary log output (#13289)

Jee Jee Li committed over 1 year ago

[V1][BugFix] Clean up rejection sampler & Fix warning msg (#13362)

Woosuk Kwon committed over 1 year ago

[Bugfix][Platform][CPU] Fix cuda platform detection on CPU backend edge case (#13358)

Isotr0py committed over 1 year ago

[V1][PP] Cache Intermediate Tensors (#13353)

Woosuk Kwon committed over 1 year ago