[BugFix][CPU] Fix CPU worker dependency on cumem_allocator (#20696)

Nick Hill committed over 1 year ago

[Frontend] Support Tool Calling with both `tool_choice='required'` and `$defs`. (#20629)

Chauncey committed over 1 year ago

Correct PPMissingLayer handling in Deepseek-V2-Lite PP deployment (#20665)

Seiji Eicher committed over 1 year ago

Use NVCC `--compress-mode` to reduce binary size by 30% (#20694)

Michael Goin committed over 1 year ago

[Misc] DP : Add ExpertTokensMetadata (#20332)

Varun Sundar Rabindranath committed over 1 year ago

[CI/Build] Fix FlashInfer double build in Dockerfile (#20651)

Michael Goin committed over 1 year ago

[Misc] Simplify the prefix caching logic on draft tokens (#20701)

Woosuk Kwon committed over 1 year ago

[BugFix]: Properly set engine_id when using multi connector (#19487)

Yiming committed over 1 year ago

[Feature][Quantization] MXFP4 support for MOE models (#17888)

fxmarty-amd committed over 1 year ago

[Kernel] Add Conch backend for mixed-precision linear layer (#19818)

Jacob Manning committed over 1 year ago

[Kernel] Triton implementation of causal-conv1d for Mamba-based models (#18218)

Tuan, Hoang-Trong committed over 1 year ago

Support Llama 4 for cutlass_moe_fp4 (#20453)

Michael Goin committed over 1 year ago

[CI/Build] Enlarge tolerance for a CPU multi-modal test (#20684)

Li, Jiang committed over 1 year ago

Remove heading form installation `inc.md` file (#20697)

Harry Mellor committed over 1 year ago

[Doc] Update CPU doc (#20676)

Li, Jiang committed over 1 year ago

[Bench] Add NVFP4 GEMM benchmark script (#20578)

Michael Goin committed over 1 year ago

[XPU][CI] enhance xpu test support (#20652)

Liangliang Ma committed over 1 year ago

[TPU][Bugfix] fix test_pallas (#20666)

Chengji Yao committed over 1 year ago

[Bugfix] Fix handling of Tensorizer arguments for LoadConfig (#20643)

Sanger Steel committed over 1 year ago

[doc] update doc format (#20673)

Reid committed over 1 year ago