biondizzle

0 Followers · 0 Following

• Joined on 2025-12-10

Repositories

25

Projects Packages Public Activity Starred Repositories

biondizzle pushed to master at biondizzle/nvfp4-megamoe-kernel 2026-05-23 21:05:15 +00:00

a762820352 D1.3: Use MLIR-compatible expression for tOrP0 offset (same as Stage C)

biondizzle pushed to master at biondizzle/nvfp4-megamoe-kernel 2026-05-23 21:03:55 +00:00

4fa4239f95 D1.3: Initialize tOrP0 before conditional for CuTeDSL scoping

biondizzle pushed to master at biondizzle/nvfp4-megamoe-kernel 2026-05-23 21:03:02 +00:00

2bb3eb95ed D1.3: Fix tOrP0 for SMEM-P - skip make_tensor when offset is 0

biondizzle pushed to master at biondizzle/nvfp4-megamoe-kernel 2026-05-23 21:02:05 +00:00

eabea91b64 D1.3: Fix tOrP0 offset - scale FP32 columns to BF16 elements

biondizzle pushed to master at biondizzle/nvfp4-megamoe-kernel 2026-05-23 21:01:20 +00:00

47eade4afc D1.3: Fix CuTeDSL scoping - define tOrP0 unconditionally with p0 offset

biondizzle pushed to master at biondizzle/nvfp4-megamoe-kernel 2026-05-23 21:00:31 +00:00

0e81fc18aa D1.3: Fix critical bug - add TMEM column offset for P0 in PV GEMM

biondizzle pushed to master at biondizzle/nvfp4-megamoe-kernel 2026-05-23 20:58:07 +00:00

29f4480e26 D1.3: Revert to d1.3-pre-sm100-helpers baseline for testing

biondizzle pushed to master at biondizzle/nvfp4-megamoe-kernel 2026-05-23 20:57:14 +00:00

adb4398505 D1.3: DIAGNOSTIC - test epilogue_tma_store raw PV without any round-trips

biondizzle pushed to master at biondizzle/nvfp4-megamoe-kernel 2026-05-23 20:56:15 +00:00

0e41816636 D1.3: Remove NO-OP round-trip, keep normalize + epilogue_tma_store

biondizzle pushed to master at biondizzle/nvfp4-megamoe-kernel 2026-05-23 20:54:29 +00:00

8bc8b21470 D1.3: Full correction_epilog with TMA store, normalize in reg before SMEM write

biondizzle pushed to master at biondizzle/nvfp4-megamoe-kernel 2026-05-23 20:52:45 +00:00

d769e01a16 D1.3: Apply transform_partitioned_tensor_layout before epilogue helpers

biondizzle pushed to master at biondizzle/nvfp4-megamoe-kernel 2026-05-23 20:50:31 +00:00

cc18fddc7e D1.3: Replace NO-op TMEM round-trip with correction_epilog using epilogue_tmem_copy_and_partition + epilogue_smem_copy_and_partition

biondizzle pushed to master at biondizzle/nvfp4-megamoe-kernel 2026-05-23 20:20:15 +00:00

993ec32567 SMEM-P: test permutation 4 (swap m↔n2)

biondizzle pushed to master at biondizzle/nvfp4-megamoe-kernel 2026-05-23 20:19:24 +00:00

c7a299d7d9 SMEM-P: add iterator offset debug print

biondizzle pushed to master at biondizzle/nvfp4-megamoe-kernel 2026-05-23 20:14:34 +00:00

4943af749d SMEM-P: add tCrP debug print, reset permute to 0

biondizzle pushed to master at biondizzle/nvfp4-megamoe-kernel 2026-05-23 20:14:22 +00:00

5a11f7c09a SMEM-P: test permutation 1 (swap m↔n0)

biondizzle pushed to master at biondizzle/nvfp4-megamoe-kernel 2026-05-23 20:13:49 +00:00

d5081fe6f0 auto: pre-test commit

biondizzle pushed to master at biondizzle/nvfp4-megamoe-kernel 2026-05-23 20:13:46 +00:00

fd54d657b2 SMEM-P: add debug_permute flag for coordinate permutation testing

biondizzle pushed to master at biondizzle/nvfp4-megamoe-kernel 2026-05-23 20:12:29 +00:00

06409401ca SMEM-P: disable debug flags, revert to original mapping

biondizzle pushed to master at biondizzle/nvfp4-megamoe-kernel 2026-05-23 20:11:51 +00:00

b8f0f0890a SMEM-P: fix scoping error, disable debug_p_one, enable debug_swap_mn