Default Branch

4975bd0c8e · [rocm-libraries] ROCm/rocm-libraries#9232 (commit 2d25e39) · Updated 2026-07-10 12:22:23 +00:00

Branches

489b0d6a37 · Bump rocm-docs-core from 1.31.3 to 1.36.0 in /docs/sphinx · Updated 2026-07-09 05:13:38 +00:00

3
1

63b3691466 · Remove the name string definition in each pipeline since it is not used · Updated 2026-07-08 15:08:36 +00:00

22
326

0b1efa2cab · Remove the name string definition in each pipeline since it is not used · Updated 2026-07-08 15:06:52 +00:00

785
316

62b879cd20 · Bump sphinxcontrib-mermaid from 2.0.2 to 2.0.3 in /docs/sphinx · Updated 2026-07-08 05:14:19 +00:00

3
1

51134d0e66 · WIP · Updated 2026-07-07 08:33:48 +00:00

24
11

61350b4380 · Synthetic test only mfma in hot loop · Updated 2026-07-01 15:21:33 +00:00

24
11

d408192bfe · Instruction scheduling in block gemm instead of scheduler · Updated 2026-07-01 13:34:22 +00:00

24
10

713f1fbf46 · [rocm-libraries] ROCm/rocm-libraries#8739 (commit 833c182) · Updated 2026-06-24 18:32:34 +00:00

18
0
Included

563f970e10 · Support OAI SwiGLU in MoE epilogue · Updated 2026-06-24 09:34:07 +00:00

169
1

43f37a22a1 · CK-UA: XCD-balanced decode grid swizzle + gated decode interleave · Updated 2026-06-24 08:27:34 +00:00

400
214

9073fa6235 · WIP: fix assembly · Updated 2026-06-23 16:32:25 +00:00

24
10

40ee1ee0af · [rocm-libraries] ROCm/rocm-libraries#8262 (commit d4ff8fc) · Updated 2026-06-16 19:10:13 +00:00

169
1

b687578c5c · Add experiment tile shape for fmha batch prefill fp8 · Updated 2026-06-16 10:41:16 +00:00

56
1

9332ef0b56 · fmha: fp8 per_token_head batch_prefill perf (v_descale fold + GEMM1 s_setprio) · Updated 2026-06-12 12:00:43 +00:00

400
220

c61dc4267e · Add tile shape for FMHA batch prefill on MI308X (on hdim=256) · Updated 2026-06-12 08:26:32 +00:00

169
1

abd84e64ab · CK-UA: correct UA_FA4_SHARED_SPCOMPUTE note (correct-but-insufficient) · Updated 2026-06-11 15:51:08 +00:00

400
206

d7bb3b10cc · [fmha-bwd] Flat cu_id remap for arbitrary CTA_NUM + grid Y/Z override env · Updated 2026-06-11 13:19:51 +00:00

3454
4049

9e0391e610 · Exp1 grid-prune: sync-free per-batch SWA dead-K-tile prune (DQDKDV) · Updated 2026-06-11 12:03:14 +00:00

400
142

78b459127b · Temporary 3way merge of ck graph fix · Updated 2026-06-10 20:32:09 +00:00

169
1

616edbcc47 · Add basic support for gfx1153 · Updated 2026-06-05 18:36:30 +00:00

1316
3