JohnnyandGitHub b4a2f3ac36 [NVIDIA] Bugfix NVFP4 DGX Spark and RTX50 (#38423) ...

Signed-off-by: johnnynunez <johnnynuca14@gmail.com>
Signed-off-by: Johnny <johnnynuca14@gmail.com>

2026-03-30 09:36:18 -07:00

..

activation_nvfp4_quant_fusion_kernels.cu

[Refactor][Kernel] Add global helper to deduplicate vectorized memory ops (#35105)

2026-02-27 16:28:17 -08:00

nvfp4_blockwise_moe_kernel.cu

[Perf] Fuse stride preparation for NVFP4 cutlass_moe (#31837)

2026-01-07 13:31:26 -05:00

nvfp4_experts_quant.cu

[Refactor][Kernel] Add global helper to deduplicate vectorized memory ops (#35105)

2026-02-27 16:28:17 -08:00

nvfp4_quant_entry.cu

[NVIDIA] Bugfix NVFP4 DGX Spark and RTX50 (#38423)

2026-03-30 09:36:18 -07:00

nvfp4_quant_kernels.cu

[Refactor][Kernel] Add global helper to deduplicate vectorized memory ops (#35105)

2026-02-27 16:28:17 -08:00

nvfp4_scaled_mm_entry.cu

[NVIDIA] Bugfix NVFP4 DGX Spark and RTX50 (#38423)

2026-03-30 09:36:18 -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

[Custom Ops] Add functional + out variant for scaled_fp4_quant (#34389)

2026-03-16 18:51:46 -04:00