787d0160a1
D1: Full test with TMEM-P at hd=64,128,256,512
2026-05-24 04:07:40 +00:00
24b9ebfba9
D1: SMEM-P test at hd=128
2026-05-24 03:48:37 +00:00
0f50933f69
D1: Fix SMEM-P (coordinate store), LSE (FP32), add TMEM-P-only test
2026-05-24 03:27:14 +00:00
f645f3994a
D1: LSE diagnostic at various hd
2026-05-24 03:23:16 +00:00
c042fcf6c7
D1: Add diagnostic test (TMEM-P vs SMEM-P at various hd)
2026-05-24 03:22:23 +00:00
1c5d6475e5
D1 test: compare un-norm O + norm using ref row_sum + LSE verification
2026-05-24 03:21:01 +00:00
93e7fe97f7
D1.5: Always output un-normalized O + LSE (epilogue_tma_store only, no TMEM round-trip normalize)
2026-05-24 03:18:38 +00:00
8010e3dda2
test: add try/except for SMEM-P coord test
2026-05-24 02:15:07 +00:00
16bade9e10
test: use FmhaKernel for SMEM-P coord test
2026-05-24 01:59:25 +00:00
f2d95da4aa
test: SMEM-P coordinate verification test
2026-05-24 01:58:32 +00:00
394f08601a
fix: proper v_major from tensor
2026-05-24 01:55:37 +00:00
384de55dfd
fix: COL_MAJOR
2026-05-24 01:54:30 +00:00
313f2c77cd
fix: hardcode v_major for diag test
2026-05-24 01:54:20 +00:00
268265ba0b
diag: use FmhaKernel setup for cotiled test
2026-05-24 01:54:08 +00:00
32d8483443
fix: v_major derivation in cotiled diag
2026-05-24 01:53:40 +00:00
ce1e2177ec
diag: simplified cotiled layout test
2026-05-24 01:53:24 +00:00
f6e3bddb10
fix: LayoutEnum import in cotiled diag test
2026-05-24 01:52:58 +00:00
67a2c3ee72
diag: layout composition test for make_cotiled_copy SMEM-P
2026-05-24 01:48:50 +00:00
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
d4aeb4e41c
D1.3: Add unnormalized debug test to isolate SMEM-P vs O round-trip error
2026-05-24 00:15:41 +00:00
b2a583a2a8
D1.3: Add SMEM-P write/read diagnostic
2026-05-24 00:13:28 +00:00
0fc6530f3f
D1.3: Add SMEM-P vs TMEM-P comparison test
2026-05-24 00:10:18 +00:00
d56e5601bb
D1.3: Fix while loop in cotiled diag - precompute num_tmem_alloc_cols
2026-05-24 00:07:22 +00:00
7bd857e5d3
D1.3: Fix cotiled diagnostic - use proper MMA construction
2026-05-24 00:06:50 +00:00
3fe17495ee
D1.3: Add make_cotiled_copy diagnostic test
2026-05-24 00:05:48 +00:00
ed539653d0
shit left dangling
2026-05-23 23:58:57 +00:00
de869c01c8
D1.3: Add SMEM-P coordinate diagnostic test
2026-05-23 23:23:05 +00:00
d10cab7a8e
D1.3: Enhanced diagnostic - test QK C-fragment as source for make_tiled_copy_C
2026-05-23 22:24:15 +00:00
a90fe41b6b
D1.3: Skip fragment creation in diagnostic, just print layouts
2026-05-23 22:21:31 +00:00
b871e6874b
D1.3: Fix diagnostic - use dummy ptr 0 for shape analysis
2026-05-23 22:20:16 +00:00
0b3d3bcd2b
D1.3: Fix sP allocation - p_smem_s.outer is already a layout
2026-05-23 22:19:11 +00:00
fc4106f37e
D1.3: Fix layout diagnostic - compute c_major outside kernel
2026-05-23 22:17:54 +00:00
6afa610b0d
D1.3: Layout diagnostic v2 - run inside JIT-compiled kernel
2026-05-23 22:16:57 +00:00
b185ac2080
D1.3: Fix layout diagnostic - remove JIT-dependent code
2026-05-23 22:15:47 +00:00
d265264f74
D1.3: Layout diagnostic - print all QK C-fragment and PV A-operand shapes
2026-05-23 22:14:35 +00:00
b1152acd88
D5b: Fix reference computation - use logsumexp for stable LSE, fix o_unnorm definition
2026-05-23 21:43:04 +00:00
b77ad244a2
D5b: Use normalized O + LSE for merge (correct formula), always output LSE
2026-05-23 21:35:40 +00:00
84200ca557
D5b: Clean up merge test - stable formula for both ref and kernel
2026-05-23 21:33:45 +00:00
909f880cc2
D5b: Use reference per-row LSE for proper O normalization
2026-05-23 21:31:52 +00:00
fef7e90c0a
D5b: Fix kernel_obj reference
2026-05-23 21:30:59 +00:00
d245342a7a
D5b: Fix syntax error
2026-05-23 21:30:00 +00:00
4a8fd64c4e
D5b: Debug reference formula mismatch, add numerically stable merge
2026-05-23 21:19:25 +00:00
e0201e581d
D5b: Python SWA+sink merge test
...
- Run FMHA twice (compressed KV + SWA KV, normalize=False)
- Merge with sink weights in Python
- Verify end-to-end correctness vs FP32 reference
2026-05-23 21:18:06 +00:00
b273d4a7e8
D5a: Add normalize flag + LSE output
...
- normalize=True (default): O = softmax(P) @ V (existing behavior)
- normalize=False: O = P @ V (un-normalized) + lse = log(row_sum) + row_max
- LSE tensor passed as optional parameter
- Test includes D5a normalize=False verification with LSE comparison
- Cleaned up SMEM-P debug prints and broken make_tiled_copy_C code
- hd=64 TMEM-P regression: cos 0.973 PASS
2026-05-23 21:10:40 +00:00
2083204a90
diag: add 2-CTA check + fix LayoutEnum in MMA test
2026-05-23 08:45:26 +00:00
02daa63f67
fix: remove bad import in NVFP4 diag
2026-05-23 08:44:37 +00:00
28724b8c18
fix: use quantize_activation_nvfp4 in diag
2026-05-23 08:39:12 +00:00
690be100aa
fix: use correct API for NVFP4-0 diag (sf_vec_size + mma_tiler_mn)
2026-05-23 08:38:19 +00:00
0fc43eb624
fix: use Sm100BlockScaledPersistentDenseGemmKernel in diag
2026-05-23 08:30:43 +00:00
e6c9616eba
fix: use randint+view for FP4/FP8 tensors in diag
2026-05-23 08:29:16 +00:00
