Commit Graph

1695 Commits

Author SHA1 Message Date
coderfeli
f9abcf80e8 use offsets in transfer ok 2025-02-07 01:54:12 +00:00
coderfeli
e947d11ea0 save outputs 2025-02-05 08:19:41 +00:00
coderfeli
9afc4a0b4d perf ok 2025-02-04 04:13:59 +00:00
coderfeli
f8d15f2af4 add others 2025-02-04 03:05:58 +00:00
coderfeli
00627feda4 results ok 2025-02-04 03:05:17 +00:00
coderfeli
6b51413b6e compile ok 2025-01-24 08:36:49 +00:00
aska-0096
b755f37502 add save_x=true instance 2025-01-13 07:12:46 +00:00
aska-0096
35ba08646f fp8 add_rmsnorm_dynamic_dequant 2025-01-10 11:12:16 +00:00
aska-0096
487a05d612 refine blockgemm pipeline version as base struct. 2025-01-08 14:27:42 +00:00
aska-0096
22fe522d0c optimize software pipeline 2025-01-08 09:28:32 +00:00
aska-0096
9dd74e0d58 tempsave 2025-01-03 02:53:55 +00:00
aska-0096
0dbe537032 refine weight preshuffle format. 2025-01-02 13:59:58 +00:00
aska-0096
72c1ddacb9 Merge branch 'add_a8w8_preshuffle_ckprofiler' of https://github.com/ROCm/composable_kernel into update_cka8w8_uc 2024-12-31 07:23:50 +00:00
aska-0096
5bbff07d40 use bpreshuffle as independent example 2024-12-31 07:20:01 +00:00
aska-0096
bbbedc1fd7 add fp16 instances 2024-12-31 07:14:56 +00:00
aska-0096
6f24c2d814 disable N, K Padding, splitk enabled 2024-12-31 06:31:06 +00:00
aska-0096
f60f9d5917 sanity pass, most tile size enabled. TODO: NWave!=4 2024-12-30 18:22:08 +00:00
aska-0096
482ca684ba Merge branch 'dev/a8w8_b_preshuffle' of https://github.com/ROCm/composable_kernel into add_a8w8_preshuffle_ckprofiler 2024-12-30 09:21:35 +00:00
aska-0096
74ef5021b6 tempsave 2024-12-30 09:20:25 +00:00
coderfeli
db84352941 fix warnings and revert cmake and fix clang format 2024-12-30 08:24:50 +00:00
coderfeli
5765ba51ce auto calculate hard code params 2024-12-30 07:59:47 +00:00
coderfeli
3f9dbcac63 use new pipeline for b preshuffle, run ok; revert olds to fix ckprofiler 2024-12-30 06:52:10 +00:00
coderfeli
54f44e6232 fix brepeat, kloop and lds two buffer; works ok now 2024-12-30 00:25:46 +00:00
coderfeli
c263bbe7e0 fix cmake rm compile options 2024-12-27 14:42:47 +00:00
coderfeli
1137424459 fix fp16 build 2024-12-27 12:39:28 +00:00
coderfeli
fda5f8cfb0 fix missed files and fix clang format 2024-12-27 11:56:46 +00:00
coderfeli
e92395d9b1 Merge remote-tracking branch 'origin/cka8w8_devtimer' into update_cka8w8_uc 2024-12-27 11:09:05 +00:00
aska-0096
7efafa1169 use empty hipstream in ckprofiler 2024-12-27 09:01:26 +00:00
coderfeli
2c056624af fix tail 2024-12-27 08:30:03 +00:00
coderfeli
174b46b04a add cpu shuffle 2024-12-27 07:31:14 +00:00
coderfeli
842d910e3c Merge branch 'update_cka8w8' into update_cka8w8_uc 2024-12-27 06:53:52 +00:00
coderfeli
e2127d7a96 impl fp16 in ckprofiler 2024-12-27 06:53:40 +00:00
coderfeli
c8d9660f3b using develop branch timer 2024-12-27 06:47:36 +00:00
coderfeli
031ddf356d fix performance regression on blockgemm v3 pipe 2024-12-27 06:40:43 +00:00
coderfeli
400cac2839 Merge branch 'develop' of https://github.com/ROCm/composable_kernel into update_cka8w8 2024-12-27 05:42:38 +00:00
coderfeli
04f09f087e fix build 2024-12-27 11:44:06 +08:00
coderfeli
1d074e34dd add configs to fix tunning cases 2024-12-27 11:43:53 +08:00
aska-0096
7cec63a631 remove agpr usage when vgpr usage <256 2024-12-27 03:09:26 +00:00
coderfeli
e6f5a78b14 add double buffer scratch 2024-12-26 15:02:04 +00:00
coderfeli
3784329b68 can run 2024-12-26 13:01:07 +00:00
coderfeli
4a1ec81595 add bypass logic and build 2024-12-26 10:05:25 +00:00
aska-0096
1a089f6f88 sanity bug fix 2024-12-26 10:05:17 +00:00
Po Yen Chen
4c2eff023a Correct the dtype checking logics (#1775) 2024-12-25 23:57:28 +08:00
coderfeli
f82c9aefcc fix build 2024-12-25 03:43:29 +00:00
coderfeli
19b7c1312c remove all non gemm in cmake 2024-12-24 07:44:12 +00:00
coderfeli
5e5e1a50f9 add instances 2024-12-24 07:43:09 +00:00
coderfeli
9ba219c875 rm debug used files 2024-12-24 03:59:12 +00:00
coderfeli
3f50b99e7b port tiles from a8w8 2024-12-23 14:13:16 +00:00
coderfeli
fc559be2d4 add configs to fix tunning cases 2024-12-23 10:36:00 +00:00
carlushuang
3d15f364b3 [CK_TILE] optimize moe-sorting kernel (#1771)
* opt moe sorting

* remove commented code
2024-12-23 10:59:02 +08:00