biondizzle 90131da010 D1.5: Replace TMEM round-trip normalize with correction epilog (one-way: TMEM→reg→SMEM→GMEM) ...

- Remove noop + normalize TMEM round-trips (3% error per trip)
- Use epilogue_tmem_copy_and_partition for TMEM→reg (paired atoms)
- Use epilogue_smem_copy_and_partition for reg→SMEM (paired atoms)
- Apply 1/row_sum normalization in register space (exact)
- TMA store from SMEM→GMEM (no TMEM write-back)
- Add iter_acc_early_release_in_epilogue attribute
- Update SMEM-P comments to reflect coordinate-indexed fallback

2026-05-24 00:24:24 +00:00

..

__init__.py

Restructure: cutedsl/ -> dsv4/ with proper layering

2026-05-21 17:30:44 +00:00

cudagraph_test.py

Restructure: cutedsl/ -> dsv4/ with proper layering

2026-05-21 17:30:44 +00:00

layertest.py

Restructure: cutedsl/ -> dsv4/ with proper layering

2026-05-21 17:30:44 +00:00

test_cutedsl.py

Restructure: cutedsl/ -> dsv4/ with proper layering

2026-05-21 17:30:44 +00:00

test_d1_3_cotiled.py

D1.3: Fix while loop in cotiled diag - precompute num_tmem_alloc_cols

2026-05-24 00:07:22 +00:00

test_d1_3_layout_diag.py

D1.3: Enhanced diagnostic - test QK C-fragment as source for make_tiled_copy_C

2026-05-23 22:24:15 +00:00

test_d1_3_smem_diag.py

D1.3: Add SMEM-P coordinate diagnostic test

2026-05-23 23:23:05 +00:00

test_d1_3_smem_direct.py

D1.5: Replace TMEM round-trip normalize with correction epilog (one-way: TMEM→reg→SMEM→GMEM)

2026-05-24 00:24:24 +00:00

test_d1_3_smem_vs_tmem.py

D1.3: Add SMEM-P vs TMEM-P comparison test

2026-05-24 00:10:18 +00:00

test_d1_3_unnorm_debug.py

D1.3: Add unnormalized debug test to isolate SMEM-P vs O round-trip error

2026-05-24 00:15:41 +00:00

test_d1_3_write_read.py

D1.3: Add SMEM-P write/read diagnostic

2026-05-24 00:13:28 +00:00

test_d1_debug.py

debug: hd=64 with CUDA_LAUNCH_BLOCKING

2026-05-23 03:42:53 +00:00

test_d1_diag.py

fix: use mV.iterator

2026-05-23 03:25:29 +00:00

test_d1_hd512.py

d1: add hd=512 test

2026-05-23 03:20:46 +00:00

test_d1_raw.py

D1: test raw unnormalized output via epilogue_tma_store

2026-05-23 03:33:59 +00:00

test_d1_regression.py

d1: add quick regression test (hd=64 only)

2026-05-23 03:20:12 +00:00

test_d1_sweep.py

D1: paired atoms epilogue (no TMEM round-trip)

2026-05-23 03:29:51 +00:00

test_fmha_v3_stage_c.py

fix: revert to composition layout for hand-constructed atoms (matching CUTLASS)

2026-05-23 02:54:54 +00:00

test_fmha_v3_stage_d1.py

D5a: Add normalize flag + LSE output

2026-05-23 21:10:40 +00:00

test_fmha_v3_stage_d5b.py

D5b: Fix reference computation - use logsumexp for stable LSE, fix o_unnorm definition

2026-05-23 21:43:04 +00:00

test_fmha_v3.py

FIX: (None,0,None,0) for ALL tma_partition outputs — verified shapes on B200

2026-05-22 23:35:55 +00:00

test_fp4_roundtrip.py

Restructure: cutedsl/ -> dsv4/ with proper layering

2026-05-21 17:30:44 +00:00

test_nvfp4_primitives.py

diag: add 2-CTA check + fix LayoutEnum in MMA test

2026-05-23 08:45:26 +00:00

test_paired_epilog.py

test: paired atoms epilog from old commit 6ee28d8

2026-05-23 03:32:53 +00:00

test_smem_p_diag.py

shit left dangling

2026-05-23 23:58:57 +00:00

test_tmem_budget.py

D1.2: fix probe for hd=512 (MMA max N=256, use pv_n_tile)

2026-05-23 06:41:42 +00:00