Public/automatic
1
0
Fork 0
mirror of https://github.com/vladmandic/automatic synced 2026-09-18 16:54:33 +02:00
Code Issues Packages Projects Releases Wiki Activity
10,034 Commits 4 Branches 34 Tags
acefa588349d2a1198734b2103442fdc7acffb06
Commit Graph

10034 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Disty0 acefa58834 SDNQ don't force fp32 with fp8 tensorwise matmul 2025-06-01 23:16:00 +03:00
Disty0 839295f79a Add fp8 fnuz to sdnq options 2025-06-01 23:10:08 +03:00
Vladimir Mandic c77162fb82 update wiki and changelog 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-06-01 21:31:43 +02:00
Disty0 539fae3234 Update naming 2025-06-01 21:01:56 +03:00
Disty0 cefe460052 SDNQ skip FP8 matmul for input len < 32 2025-05-31 01:27:59 +03:00
Disty0 046840c8be Fix HiDream sampling 2025-05-31 00:52:56 +03:00
Disty0 109c0d7e49 SDNQ use tensorwise FP8 matmul on CPU 2025-05-30 21:09:53 +03:00
Disty0 959b759721 Cleanup 2025-05-30 16:45:59 +03:00
Disty0 b5d588fa45 SDNQ remove unnecessary bitwise ands 2025-05-30 16:29:59 +03:00
Disty0 db816d7088 Cleanup 2025-05-30 16:02:26 +03:00
Disty0 c85cc6b397 SDNQ enable quant with GPU by default and don't do unnecessary clones 2025-05-30 15:21:29 +03:00
Disty0 4654acde3c SDNQ re-enable memory fix for diffusers 2025-05-30 14:59:45 +03:00
Disty0 87a801e24d SDNQ remove memory fix hijack 2025-05-30 13:54:49 +03:00
Disty0 f81cb22c00 SDNQ fix new transformers 2025-05-30 13:32:03 +03:00
Disty0 36febda6e6 SDNQ update supported dtypes 2025-05-30 13:07:23 +03:00
Disty0 29bd2af779 SDNQ add 6-bit support 2025-05-30 12:20:13 +03:00
Vladimir Mandic 98a11fc86c fix gallery duplicate entries 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-05-30 11:04:56 +02:00
Vladimir Mandic 9168a66fd2 update requirements 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-05-30 08:53:39 +02:00
Vladimir Mandic 4e184f41af update changelog 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-05-30 08:44:30 +02:00
Disty0 d1491962d9 One bit 2025-05-30 05:41:02 +03:00
Disty0 3c8be0f55f SDNQ add uint2 2025-05-30 04:47:29 +03:00
Disty0 599224d392 SDNQ reduce 5 reshape ops to 2 with quantized input 2025-05-30 01:31:41 +03:00
Disty0 d8dea9031f SDNQ do FP8 matmul shape check only once 2025-05-30 01:13:37 +03:00
Disty0 b4e615e760 SDNQ add FP8 row wise scaling workaround for SM89 on Windows 2025-05-30 00:16:54 +03:00
Disty0 54154cf698 Cleanup 2025-05-29 20:22:49 +03:00
Disty0 90324f9c8c SDNQ fix lora with quant matmul 2025-05-29 18:25:12 +03:00
Disty0 df8b31fcfc Don't downcast scale with fp8 matmul 2025-05-29 16:35:40 +03:00
Disty0 2351efb8f7 Remove redundant shape check 2025-05-29 14:58:00 +03:00
Disty0 14893b7617 Don't make the weights contiguous with int8 matmul 2025-05-29 03:43:57 +03:00
Disty0 cf2d1e56a6 Update changelog 2025-05-29 03:32:11 +03:00
Disty0 2cc5a58b0f Update changelog 2025-05-29 03:26:47 +03:00
Disty0 67e0f4d833 Cleanup 2025-05-29 03:22:40 +03:00
Disty0 3698f8bb84 SDNQ add experimental FP8 matmul 2025-05-29 03:11:59 +03:00
Disty0 dd33c4d583 Fix scale and zero_point not being moved by tensor.to 2025-05-28 17:46:06 +03:00
Disty0 dd0dbc476f SDNQ fix asym quant formula for dtypes with non zero minimums 2025-05-28 17:25:38 +03:00
Disty0 e06cbea7aa Cleanup 2025-05-28 15:55:08 +03:00
Disty0 d8e8f47ce5 SDNQ add an option to toggle quantize with GPU 2025-05-28 15:18:39 +03:00
Disty0 1961e88c13 Set SDPA as the default on all backends and enable Dyn SDPA on ROCm, DML, CPU and MPS 2025-05-28 13:42:29 +03:00
Disty0 569e9099d7 Use torch.amax instead of torch.max 2025-05-28 12:44:07 +03:00
Disty0 0b564e2373 Cleanup 2025-05-28 04:07:45 +03:00
Disty0 1433dfe3de SDNQ fix high RAM usage with pre mode 2025-05-28 03:16:29 +03:00
Disty0 4ed15f5cce SDNQ revert device_map = gpu 2025-05-27 23:32:58 +03:00
Disty0 d3e3fb98b0 Don't override user set device_map 2025-05-27 21:45:52 +03:00
Disty0 b1b29e9001 SDNQ disable device_map = gpu with TE and LLM 2025-05-27 21:32:32 +03:00
Disty0 b724cd7c57 Update changelog 2025-05-27 21:21:42 +03:00
Disty0 5d3c1832b2 SDNQ add FP8 quants 2025-05-27 20:29:15 +03:00
Disty0 3618e39cff SDNQ use device_map = gpu 2025-05-27 19:46:30 +03:00
Disty0 73999ac710 Add soft gc to nncf quant layer 2025-05-27 16:24:04 +03:00
Disty0 e94128a02e SDNQ add force torch_gc to pre load mode 2025-05-27 16:11:04 +03:00
Disty0 dece497f10 Refactor SDNQ to use weights_dtype and rename decompress_int8_matmul to use_quantized_matmul 2025-05-27 15:49:21 +03:00