Roberto L. CastroandGitHub 789562c28c Support CUTLASS NVFP4 (w4a4) for Blackwell Geforce GPUs (SM120) (#21309) ...

Signed-off-by: LopezCastroRoberto <roberto.lopez.castro@udc.es>

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

..

nvfp4_blockwise_moe_kernel.cu

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

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

nvfp4_experts_quant.cu

[Bugfix] Fix some narrowing conversion warnings (#20141)

2025-06-27 09:01:28 -07:00

nvfp4_quant_entry.cu

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

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

nvfp4_quant_kernels.cu

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

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

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