Vladimir Mandic
|
bfe014f5da
|
modernize typing
|
2026-02-19 09:15:37 +01:00 |
|
Disty0
|
bc7c89c070
|
add typing to sdpa hijacks
|
2025-09-10 04:43:57 +03:00 |
|
Disty0
|
ad716b118b
|
fix enable_gqa with dyn atten
|
2025-07-26 01:49:17 +03:00 |
|
Disty0
|
90f887ac4a
|
Add dim checks to ck flash atten and fix dim check on dyn atten
|
2025-03-25 03:50:21 +03:00 |
|
Disty0
|
675956010f
|
Multiply the slice rate for dyn bmm by 4
|
2025-01-30 18:44:26 +03:00 |
|
Vladimir Mandic
|
6960b05129
|
lint and update changelog
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-01-28 09:02:44 -05:00 |
|
Disty0
|
b0ecdf2f1c
|
Better dyn atten sdpa usage estimation logic
|
2025-01-26 16:57:26 +03:00 |
|
Disty0
|
bb07dd7a8f
|
Add trigger rate control to dyn atten
|
2025-01-26 03:48:01 +03:00 |
|
Disty0
|
3f2c9c4e22
|
Fix dyn atten not registering slice rate changes
|
2025-01-25 22:44:29 +03:00 |
|
Disty0
|
d266143f20
|
Cleanup
|
2025-01-25 21:46:23 +03:00 |
|
Disty0
|
02ecc6710d
|
Fix missing unsqueeze
|
2025-01-25 21:43:38 +03:00 |
|
Disty0
|
a770b1c888
|
More correct Dynamic Atten SDPA implementation and deprecate IPEX Diffusers attention
|
2025-01-25 21:33:42 +03:00 |
|
Disty0
|
85c3a76c1a
|
Dynamic Atten use expand instead of repeat
|
2024-10-25 21:06:46 +03:00 |
|
Disty0
|
7d56d5b72c
|
Dynamic atten don't repeat the last shape of atten masks
|
2024-10-25 13:45:20 +03:00 |
|
Disty0
|
3e268e7cea
|
Cleanup
|
2024-10-24 21:53:33 +03:00 |
|
Disty0
|
3195e8ad1f
|
Dynamic Atten fix OmniGen
|
2024-10-24 21:22:06 +03:00 |
|
Disty0
|
2e2cb43406
|
Make SDPA hijacks chainable and add Sage Attention
|
2024-10-12 21:19:38 +03:00 |
|
Vladimir Mandic
|
f2c5cbbb36
|
lint updates and diffusers installer
|
2024-09-06 14:10:53 -04:00 |
|
Disty0
|
a3f26c9df0
|
Convert Dynamic Attention SDP to a global SDP option
|
2024-08-18 01:44:27 +03:00 |
|
Disty0
|
bbaec29720
|
Cleanup
|
2024-06-21 21:07:15 +03:00 |
|
Disty0
|
c9e01b4a32
|
OpenVINO fix --device-id with single GPU
|
2024-02-12 01:57:27 +03:00 |
|
Disty0
|
3f8da51eac
|
Set default atten for ROCm to SDP
|
2024-02-11 13:44:39 +03:00 |
|
Disty0
|
0ac2dfbcaa
|
Dyn Atten don't synchronize if not slicing
|
2024-02-10 20:02:29 +03:00 |
|
Disty0
|
43c5be76ca
|
Unite attention optimization settings
|
2024-02-10 10:32:53 -05:00 |
|