Michael GoinandGitHub e502098643 [Kernel] Add NVFP4 MoE CUTLASS support for SM120 (#29242) ...

Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>

2025-11-25 06:59:07 -08:00

..

activation_nvfp4_quant_fusion_kernels.cu

[Compile] Fix Compile Warning for Ignoring MIN_BLOCK_PER_SM (#25193)

2025-09-19 16:23:19 -06:00

nvfp4_blockwise_moe_kernel.cu

[Kernel] Add NVFP4 MoE CUTLASS support for SM120 (#29242)

2025-11-25 06:59:07 -08:00

nvfp4_experts_quant.cu

[Kernel] Add NVFP4 MoE CUTLASS support for SM120 (#29242)

2025-11-25 06:59:07 -08:00

nvfp4_quant_entry.cu

[Kernel] Add NVFP4 MoE CUTLASS support for SM120 (#29242)

2025-11-25 06:59:07 -08:00

nvfp4_quant_kernels.cu

[Bugfix] Use latency MOE backend as default for Flashinfer and other misc fixes (#27439)

2025-11-07 04:18:39 -08:00

nvfp4_scaled_mm_entry.cu

Support CUTLASS NVFP4 (w4a4) for Blackwell Geforce GPUs (SM120) (#21309)

2025-08-03 00:54:22 -07:00

nvfp4_scaled_mm_kernels.cu

[Kernel] Basic tuned configs for NVFP4 CUTLASS dense GEMM (#20646)

2025-07-11 10:05:33 -06:00

nvfp4_scaled_mm_sm120_kernels.cu

Support CUTLASS NVFP4 (w4a4) for Blackwell Geforce GPUs (SM120) (#21309)

2025-08-03 00:54:22 -07:00

nvfp4_utils.cuh

[Bugfix][Misc] Fix silu_and_mul_nvfp4_quant issue and extract common utils for nvfp4 kernel source files (#23727)

2025-09-04 14:25:45 -07:00