[Model][Speculative Decoding] Expand DeepSeek MTP code to support k > n_predict (#13626)

Benjamin Chislett committed over 1 year ago

[Attention] Flash MLA for V1 (#13867)

Lucas Wilkinson committed over 1 year ago

[core] Perf improvement for DSv3 on AMD GPUs (#13718)

qli88 committed over 1 year ago

[V1][Minor] Minor cleanup for GPU Model Runner (#13983)

Woosuk Kwon committed over 1 year ago

[ROCm] Fix the Kernels, Core, and Prefix Caching AMD CI groups (#13970)

Sage Moore committed over 1 year ago

[VLM] Deprecate legacy input mapper for OOT multimodal models (#13979)

Cyrus Leung committed over 1 year ago

Bump azure/setup-helm from 4.2.0 to 4.3.0 (#13742)

dependabot[bot] committed over 1 year ago

[Attention] MLA support for V1 (#13789)

Yang Chen committed over 1 year ago

[VLM] Generalized prompt updates for multi-modal processor (#13964)

Cyrus Leung committed over 1 year ago

[Bugfix] Fix qwen2.5-vl overflow issue (#13968)

Isotr0py committed over 1 year ago

Update LMFE version to v0.10.11 to support new versions of transforme… (#13930)

Noam Gat committed over 1 year ago

[bugfix] Fix profiling for RayDistributedExecutor (#13945)

Rui Qiao committed over 1 year ago

Deduplicate `.pre-commit-config.yaml`'s `exclude` (#13967)

Harry Mellor committed over 1 year ago

Update quickstart.md (#13958)

王博伟 committed over 1 year ago

[Model] Deepseek GGUF support (#13167)

Szymon Ożóg committed over 1 year ago

[VLM] Support multimodal inputs for Florence-2 models (#13320)

Isotr0py committed over 1 year ago

Fix test_block_fp8.py test for MoE (#13915)

Michael Goin committed over 1 year ago

[PP] Correct cache size check (#13873)

Yang Zheng committed over 1 year ago

[Misc] fixed 'required' is an invalid argument for positionals (#13948)

Chauncey committed over 1 year ago

[CI/Build] Add examples/ directory to be labelled by `mergify` (#13944)

Brayden Zhong committed over 1 year ago