biondizzle 755f9ad567 debug: fix per_expert_alpha ref + clean up BF16 reference scaling

2026-05-15 17:55:11 +00:00

..

cutlass_nvfp4_gemm

fix: stop folding global scale into float8 block scales

2026-05-15 12:42:53 +00:00

__init__.py

feat: CUTLASS NVFP4 mega_moe kernel — slot-based L1/L2, source-first SF remap

2026-05-15 11:38:18 +00:00

nvfp4_mega_moe.py

debug: fix per_expert_alpha ref + clean up BF16 reference scaling

2026-05-15 17:55:11 +00:00

symm_buffer.py

feat: CUTLASS NVFP4 mega_moe kernel — slot-based L1/L2, source-first SF remap

2026-05-15 11:38:18 +00:00

weight_transform.py

fix: stop folding global scale into float8 block scales

2026-05-15 12:42:53 +00:00