lyrisz 97e3dda84b

[Perf] SM100 - add swap AB optimization to CUTLASS FP8 GEMM (#27284) ...

Signed-off-by: Faqin Zhong <faqin.zhong@gmail.com>
Co-authored-by: Faqin Zhong <zhofaqin@amazon.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>

2025-11-04 07:49:25 -08:00

..

awq

…

cutlass_w4a8

[Kernel] Faster pre-processing time for W4A8 (#23972)

2025-09-17 14:35:32 -07:00

fp4

[CI/Build] Conditionally register cutlass_fp4_group_mm to fix building on Hopper (#26138)

2025-10-02 20:32:38 -07:00

fused_kernels

[torch.compile] Enable attention and allreduce fusion without custom ops enabled (#24604)

2025-10-17 08:10:23 -06:00

gguf

…

gptq

[Kernel] Add GPTQv2 format support for low-bit or asymmetric quantization, by adapting gptq_gemm (#26092)

2025-10-23 23:26:13 -04:00

gptq_allspark

…

gptq_marlin

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

hadamard/hadacore

[Transform] Deterministic Hadacore Transforms (#24106)

2025-09-15 12:59:31 -06:00

machete

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

marlin/sparse

…

w8a8

[Perf] SM100 - add swap AB optimization to CUTLASS FP8 GEMM (#27284)

2025-11-04 07:49:25 -08:00

activation_kernels.cu

Silu v2 (#25074)

2025-10-10 15:19:53 +00:00

utils.cuh

…

vectorization_utils.cuh

Make sure that vectorize_with_alignment produced vectorized global loads (#23182)

2025-08-21 20:06:54 +00:00

vectorization.cuh

…