[Model] Add ColPali late interaction model for multi-modal retrieval (#36818)

Nikita committed 8 months ago

[BUG] Fix rank calculation in NCCLWeightTransferEngine (#36940)

Aaron Hao committed 8 months ago

build: update smg-grpc-servicer to use vllm extra (#36938)

Simo Lin committed 8 months ago

[Bugfix] ep_scatter kernel store-load race condition (#34991)

Yifan Qiao committed 8 months ago

[Model Runner V2] Some code simplification (#36929)

Nick Hill committed 8 months ago

[MoE] Add routing simulation override for MXFP4 quantized MoE (#33595)

Jaewon committed 8 months ago

[Speculative Decoding] Add `norm_before_fc` for gpt-oss draft models (#36545)

Shubhra Pandit committed 8 months ago

[AMD][Build] Add DeepEP to ROCm Dockerfile (#36086)

Ryan Rock committed 8 months ago

[ROCm][CI] Preparing gfx90a mirroring (#36210)

Andreas Karatzas committed 8 months ago

Revise environment setup in AGENTS.md (#36909)

Michael Goin committed 8 months ago

[Feature]: Remove Chunking From FusedMoE (#34086)

Xinan Miao committed 8 months ago

[bnb] Skip moe + bnb test (#36896)

Marc Sun committed 8 months ago

Add `AGENTS.md` (#36877)

Harry Mellor committed 8 months ago

Update Flashinfer to 0.6.6 (#36768)

Dimitrios Bariamis committed 8 months ago

[Bugfix] Fix KeyError in parse_response_input for reasoning items with optional content (#34499)

Eunkwang Jeon committed 8 months ago

[Attention] Use FA4 for MLA prefill (#34732)

Matthew Bonanni committed 8 months ago

[Bugfix] fix main branch pre-commit error (1 line change) (#36897)

SoluMilken committed 8 months ago

[Kernel] Add FP8 KV cache support to Triton MLA decode attention (#34597)

grimulkan committed 8 months ago

[CI] Fix mypy pre-commit errors on main (#36882)

Thomas Parnell committed 8 months ago

[Hardware] Replace torch.cuda.device_count/current_device/set_device API (#36145)

Kunshang Ji committed 8 months ago