[Agents] Expose Triton kernel-writing skill to Claude (#55028)

Woosuk Kwon committed about 2 months ago

[Agents] Add Triton kernel-writing skill (#55019)

Woosuk Kwon committed about 2 months ago

[CI] Remove deleted nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 and its arch aliases (#55026)

Kevin H. Luu committed about 2 months ago

[XPU] Add fused GemmaRMSNorm path for eager execution (#53678)

Huanxing committed about 2 months ago

[CI] Exclude nightly-dev tags from nightly DockerHub cleanup (#55023)

Kevin H. Luu committed about 2 months ago

[ROCm][CI] Extend Multimodal Processor Shard timeout on AMD CI (#55011)

Micah Williamson committed about 2 months ago

[Bugfix][Rust Frontend][Renderer] Align DeepSeek V4 historical developer message handling (#54854)

Reid committed about 2 months ago

[K3 Perf] Enable DSV3 GEMM for inner-contiguous and row-strided tensors, 12%~81% kernel performance improvement (#54565)

Wentao Ye committed about 2 months ago

[ROCm][CI] Fix false multi-node detection on native CI (#54989)

Sheral Kumar committed about 2 months ago

[Bugfix][Tests] Stabilize B12X linear kernel checks (#54996)

Luke Alonso committed about 2 months ago

[CI][MoE] Moe kernels test cleanup (#54954)

stefankoncarevic committed about 2 months ago

[CI/Build][ROCm] Guard the two CUDA-only tests in test_bf16_skinny_gemm (#54984)

stefankoncarevic committed about 2 months ago

[Bugfix][CI] Set cudagraph_mode=FULL for the Ernie4.5-VL ViT cudagraph test (#54957)

stefankoncarevic committed about 2 months ago

[CI][ROCm] Add DSpark evals (#54852)

Andreas Karatzas committed about 2 months ago

[New model][Multimodal] Add DeepSeek-V4-Flash-Vision-Exp support (#54566)

Isotr0py committed about 2 months ago

[CI] Revert flaky `test_quark_int8_w8a8_moe` (#54991)

fxmarty-amd committed about 2 months ago

[BUILD] Bump cutlass to v4.7.1 (#54190)

Shengqi Chen committed about 2 months ago

[Docs] Add missing return annotations flagged by griffe (#54980)

Harry Mellor committed about 2 months ago

[Bugfix][Model] Fix CohereASR streaming audio-token estimate (unit + subsampling) (#53829)

Hung Hoang (黄兴） committed about 2 months ago

[NIXL] Use int32 array for indices to avoid intermediate conversion (#51952)

Ilia Yastrebov committed about 2 months ago