Commit Graph

22 Commits (10bbbed218458b8a899aac2140ec738d8d716f05)

Author SHA1 Message Date
Disty0 2104bf8bb0 sdnq add wan keys 2025-10-25 15:34:14 +03:00
Disty0 4aee524ddf SDNQ add NaDiT keys 2025-10-14 17:18:58 +03:00
Disty0 b601f0d402 SDNQ expose svd_steps and update module skip keys 2025-10-14 00:15:09 +03:00
Disty0 a376f89fd6 Add type checking to SDNQConfig 2025-10-12 01:02:47 +03:00
Disty0 df142afe81 don't use triton mm for nvidia 2025-10-04 18:48:03 +03:00
Disty0 5c5d7d5a86 cleanup 2025-10-04 18:38:18 +03:00
Disty0 99113947bf SDNQ add RDNA2 INT8 support via Triton 2025-10-04 18:31:25 +03:00
Disty0 34c2a624aa SDNQ autodetect fp8 tw fallback and disable dynamic compile 2025-10-02 19:40:07 +03:00
Disty0 1b45c145e9 SDNQ re-enable dynamic compile 2025-09-28 20:40:24 +03:00
Disty0 71fde8a897 ROCm and Zluda don't fallback to CPU and clenup strings 2025-09-27 11:32:46 +03:00
Vladimir Mandic 5b43c66a92 nunchaku sdxl and sdxl-turbo support
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-20 21:01:21 -04:00
Disty0 e6715ba8d3 Cleanup SDNQ compile 2025-09-19 19:29:36 +03:00
Vladimir Mandic 9743c8e4bf keep previous processed state
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-08-31 15:20:15 -04:00
Disty0 a8de3f7282 SDNQ add quantized matmul support for all quantization types and group sizes 2025-08-29 22:26:47 +03:00
Disty0 dc7b25d387 Cleanup SDNQ and add SDNQ_USE_TENSORWISE_FP8_MATMUL env var 2025-08-11 14:50:17 +03:00
Disty0 c3d007b02c SDNQ split forward.py into layers and cleanup 2025-08-02 17:36:55 +03:00
Vladimir Mandic 2656d3aa68 lint
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-07-24 15:42:29 -04:00
Disty0 444974a6ff cleanup 2025-07-23 19:02:44 +03:00
Disty0 7a08e1a7f2 SDNQ always use custom tensorwise fp8 matmul 2025-07-23 19:01:10 +03:00
Disty0 e43d1d2ba7 SDNQ use strings as target_dtype 2025-06-25 23:25:49 +03:00
Disty0 33fadf946b SDNQ add 7 bit support 2025-06-10 11:33:06 +03:00
Disty0 5eed9135e3 Split SDNQ into multiple files and linting 2025-06-10 03:18:25 +03:00