Default Branch

2089713f94 · [rocm-libraries] ROCm/rocm-libraries#8227 (commit 75c30d5) · Updated 2026-06-26 12:00:58 +00:00

Branches

7ec221fb21 · Profile only default split-K value. · Updated 2025-08-01 13:35:29 +00:00    ROCm

1368
61

6632443ae4 · Merge remote-tracking branch 'origin/develop' into cderb/tuning_250729 · Updated 2025-07-31 03:15:07 +00:00    ROCm

1291
10

c1548bf08c · Fix issues after merge · Updated 2025-07-30 15:51:46 +00:00    ROCm

1296
17

ab80fd3d7f · first commit · Updated 2025-07-30 02:36:06 +00:00    ROCm

1296
1

35ac1894ba · update codes · Updated 2025-07-29 08:43:52 +00:00    ROCm

1353
17

9d4b494f07 · Expand the bandwidth of direct_global_to_lds for gfx950 (#2576) · Updated 2025-07-29 06:56:53 +00:00    ROCm

1296
0
Included

62855271b9 · modify the instances; optimize atomic pattern; set B gmem to NT mode · Updated 2025-07-29 02:30:00 +00:00    ROCm

1497
3

42b2e3bc40 · change Atrribute to Attribute globally · Updated 2025-07-28 19:43:08 +00:00    ROCm

1303
86

bfdfd1e148 · fix reference · Updated 2025-07-28 08:11:15 +00:00    ROCm

1543
24

03e3509226 · Fix CI build due to #2542 · Updated 2025-07-25 16:39:54 +00:00    ROCm

1313
1

7ea611bb5d · test pip packages installation · Updated 2025-07-25 05:21:46 +00:00    ROCm

1315
1

073de8e3a1 · group ptpc gemm. Files prepared. No change made yet · Updated 2025-07-24 02:12:51 +00:00    ROCm

1326
1

2b5a211f01 · Fix swa condition in bwd_api (#2541) · Updated 2025-07-23 14:03:38 +00:00    ROCm

1676
78

a5fdc663c8 · fix async copytest bug (#2509) · Updated 2025-07-23 07:14:02 +00:00    ROCm

1328
0
Included

769fbb62d5 · epilogue switched to cshuffle · Updated 2025-07-23 03:40:15 +00:00    ROCm

1339
25

67b2821623 · Switch to C++20 standard for all CMake targets. (#2536) · Updated 2025-07-22 17:52:10 +00:00    ROCm

1330
0
Included

c77958e4bf · Update conf.py · Updated 2025-07-22 14:30:33 +00:00    ROCm

1759
11

5c43185d75 · tempsave · Updated 2025-07-22 09:50:41 +00:00    ROCm

1339
25

f2d2956434 · add gemm2 persisitent · Updated 2025-07-22 03:18:12 +00:00    ROCm

1387
7

008f64ad6d · Merge branch 'develop' into moe_bs_fp8_no_asm_buf2lds · Updated 2025-07-22 02:02:02 +00:00    ROCm

1355
132