biondizzle
  • Joined on 2025-12-10
biondizzle pushed to master at biondizzle/nvfp4-megamoe-kernel 2026-05-24 01:55:39 +00:00
3325d7442c fix: proper v_major from tensor
biondizzle pushed to master at biondizzle/nvfp4-megamoe-kernel 2026-05-24 01:54:32 +00:00
f2dd36cd4b fix: COL_MAJOR
biondizzle pushed to master at biondizzle/nvfp4-megamoe-kernel 2026-05-24 01:54:21 +00:00
c815560d64 fix: hardcode v_major for diag test
biondizzle pushed to master at biondizzle/nvfp4-megamoe-kernel 2026-05-24 01:54:10 +00:00
34fe43a551 diag: use FmhaKernel setup for cotiled test
biondizzle pushed to master at biondizzle/nvfp4-megamoe-kernel 2026-05-24 01:53:43 +00:00
7a9881ab82 fix: v_major derivation in cotiled diag
biondizzle pushed to master at biondizzle/nvfp4-megamoe-kernel 2026-05-24 01:53:26 +00:00
a5fbc6cebd diag: simplified cotiled layout test
biondizzle pushed to master at biondizzle/nvfp4-megamoe-kernel 2026-05-24 01:53:01 +00:00
60ff5e4f53 fix: LayoutEnum import in cotiled diag test
biondizzle pushed to master at biondizzle/nvfp4-megamoe-kernel 2026-05-24 01:48:51 +00:00
7113da195b diag: layout composition test for make_cotiled_copy SMEM-P
biondizzle pushed to master at biondizzle/nvfp4-megamoe-kernel 2026-05-24 01:41:54 +00:00
8166898cc3 D1.5: Fix bSG_gC slicing - group trailing modes (CUTLASS pattern)
biondizzle pushed to master at biondizzle/nvfp4-megamoe-kernel 2026-05-24 01:40:47 +00:00
c7a692b75e D1.5: Dynamic slicing for tTR_gC (variable rest dims)
biondizzle pushed to master at biondizzle/nvfp4-megamoe-kernel 2026-05-24 01:39:22 +00:00
cb6eae4c4f D1.5: Fix flat_divide slice coordinates (4 modes, no STAGE dim)
biondizzle pushed to master at biondizzle/nvfp4-megamoe-kernel 2026-05-24 01:37:54 +00:00
d6a607d12e D1.5: Rewrite correction epilogue using CUTLASS pattern (transform_partitioned, flat_divide, paired atoms)
biondizzle pushed to master at biondizzle/nvfp4-megamoe-kernel 2026-05-24 01:36:03 +00:00
ef9fa86848 D1.5: Fix TMA store - group_modes on bSG_gC, use flat indexing
biondizzle pushed to master at biondizzle/nvfp4-megamoe-kernel 2026-05-24 01:35:12 +00:00
5a5cd19b81 D1.5: Fix TMA store - use flat_divide on tCgC instead of local_tile on mC
biondizzle pushed to master at biondizzle/nvfp4-megamoe-kernel 2026-05-24 01:20:35 +00:00
52a5aa61bc D1.5: Fix TMA store - use 3D tile for local_tile on 3D mC
biondizzle pushed to master at biondizzle/nvfp4-megamoe-kernel 2026-05-24 00:52:59 +00:00
865832f669 D1.5: Use group_modes on sC for 2D TMA view (preserves swizzle)
biondizzle pushed to master at biondizzle/nvfp4-megamoe-kernel 2026-05-24 00:51:20 +00:00
a8939ced1f D1.5: Use 2D sC_epi layout from c_smem_s for TMA partition
biondizzle pushed to master at biondizzle/nvfp4-megamoe-kernel 2026-05-24 00:48:20 +00:00
9705b07969 D1.5: Fix TMA store - use group_modes on sC and tCgC
biondizzle pushed to master at biondizzle/nvfp4-megamoe-kernel 2026-05-24 00:46:53 +00:00
d834836bb7 D1.5: Simplify TMA store - use 2D sC_epi and gC_epi views
biondizzle pushed to master at biondizzle/nvfp4-megamoe-kernel 2026-05-24 00:43:36 +00:00
c05a171e15 D1.5: Fix TMA store - use existing gC partition