Default Branch

55e30feac6 · [rocm-libraries] ROCm/rocm-libraries#8637 (commit a1a7f5f) · Updated 2026-06-20 02:08:58 +00:00

Branches

6670e53589 · Fix instruction scheduler · Updated 2026-06-20 12:21:35 +00:00

2
9

c2e187e997 · Allow broadcasting of D column vectors in DeviceGemmMultiD_Xdl_CShuffle_V3 · Updated 2026-06-19 13:50:56 +00:00

2
7

2694adbd55 · Remove the using of kSubQKHeaddim · Updated 2026-06-19 05:17:35 +00:00

763
305

0b43e6d159 · Remove the using of kSubQKHeaddim · Updated 2026-06-19 05:16:40 +00:00

763
308

cd782f613c · Fix buffer load instruction 7.2 · Updated 2026-06-18 10:49:01 +00:00

17
6

0765b2631b · CK-UA: aggressive pipeline cleanup — drop dead experiments + trim comments · Updated 2026-06-17 11:39:10 +00:00

378
213

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

147
1

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

34
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

378
220

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

147
1

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

378
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

3432
4049

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

378
142

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

147
1

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

1294
3

82ee798809 · Fix nsplits to min(8, nc) for chunk-level dyn_naive load balancing under NCCL overlap · Updated 2026-06-02 19:58:12 +00:00

3432
4048

64d3e00077 · Merge remote-tracking branch 'origin/dlejeune/ua-swa-v2' into jukorhon/unified-attention-ck · Updated 2026-06-01 12:45:43 +00:00

378
194

3f930e18f5 · UA sink: add instances for fp8 · Updated 2026-05-29 13:56:23 +00:00

378
199

2b4020af0d · Merge branch 'jukorhon/unified-attention-ck' into dlejeune/ua-swa-v2 · Updated 2026-05-28 09:18:57 +00:00

378
190

58e2ab1fc7 · [rocm-libraries] ROCm/rocm-libraries#6761 (commit d19f6f1) · Updated 2026-05-27 18:55:15 +00:00

92
0
Included