Commit Graph

11064 Commits

Author SHA1 Message Date
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
Vladimir Mandic 21816b3bb7 Merge pull request #4250 from liutyi/dev
SD1.5 and SD2.1 updated cover images
2025-10-04 09:08:39 -04:00
Oleksandr Liutyi e5ef08d490 SD1.5 and SD2.1 updated cover images 2025-10-04 12:18:17 +03:00
Vladimir Mandic 54ae18a611 update nunchaku
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-10-03 12:23:24 -04:00
Disty0 95a7da7e75 SDNQ use non-contiguous re-quantize 2025-10-03 18:54:58 +03:00
Vladimir Mandic a6108dd6df add qwen pruning variants
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-10-03 11:36:14 -04:00
Disty0 54acf1760b Make SDNQ scales compatible with balanced offload 2025-10-03 18:13:55 +03:00
Disty0 c5cab96223 SDNQ simplify check_mats 2025-10-03 02:58:17 +03:00
Vladimir Mandic 75773eb3cc lock diffusers version for rocm/zluda
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-10-02 17:38:07 -04:00
Vladimir Mandic 7325f9dbae dont import guiders until needed
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-10-02 16:28:34 -04:00
Disty0 34c2a624aa SDNQ autodetect fp8 tw fallback and disable dynamic compile 2025-10-02 19:40:07 +03:00
Vladimir Mandic a0b375ae3d update diffusers to unblock rocm
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-10-02 12:19:54 -04:00
Vladimir Mandic f245506bf2 cleanup hf login
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-10-02 08:17:35 -04:00
Vladimir Mandic 435ec70f60 Merge pull request #4248 from CalamitousFelicitousness/patch-2
Allow 0 in VLM temp setting
2025-10-02 08:10:46 -04:00
CalamitousFelicitousness 78711fb1d4 Merge branch 'dev' into patch-2 2025-10-01 20:58:58 +01:00
CalamitousFelicitousness 78820a14dc Allow VLM temp setting temperature to 0
Allow VLM temp setting temperature to 0
2025-10-01 20:52:04 +01:00
Vladimir Mandic 450464aa92 update todo
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-10-01 15:24:37 -04:00
Vladimir Mandic 7bae6c2c83 add florence/promptgen info to changelog
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-10-01 14:45:07 -04:00
Vladimir Mandic ec7b22e383 warn on startup if cuda/rocm are available and torch-cpu is installed
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-10-01 14:45:07 -04:00
Disty0 81bb2b99ef update florence promptgen repo ids 2025-10-01 21:43:02 +03:00
Vladimir Mandic 22074f4727 cleanup vqa
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-10-01 12:02:55 -04:00
Vladimir Mandic 5d0a3e5e8a fix microsoft-florence
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-10-01 10:58:52 -04:00
Vladimir Mandic 1fcf12d874 lock diffusers versions for zluda/rocm/directml
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-10-01 10:24:22 -04:00
Disty0 03382bdd4c SDNQ simplify check_mats 2025-10-01 01:35:51 +03:00
Vladimir Mandic 8c2b76a8da add buffers and cache info
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-30 14:36:55 -04:00
Vladimir Mandic 201ca28300 improve ram monitor
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-30 14:27:43 -04:00
Vladimir Mandic 228037e08f Merge pull request #4242 from liutyi/dev
More model covers updated (Tempest,..)
2025-09-30 10:06:42 -04:00
Oleksandr Liutyi 24c44af42f embed prompts to Tempest model, similar prompt for base and hyper 2025-09-30 15:27:49 +03:00
Disty0 0c1d34721c SDNQ use contiguous for intel 2025-09-30 02:37:58 +03:00
Vladimir Mandic 2621aecacc interrrupt will now show last known preview image
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-29 19:25:50 -04:00
Disty0 6b67a9d0c4 SDNQ add check_mats to matmul 2025-09-30 01:58:13 +03:00
Vladimir Mandic 3084c3214f disable transformers TOKENIZERS_PARALLELISM
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-29 16:33:03 -04:00
Vladimir Mandic 00fa1dc59e add online/offline since
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-29 11:46:00 -04:00
Disty0 206c795207 add Intel Graphics Software to autodetect 2025-09-29 18:36:20 +03:00
Vladimir Mandic 93bdca0670 fix image str decode and update requirements
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-29 10:56:03 -04:00
Vladimir Mandic 5d1bfc2bfc cleanup
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-28 21:36:16 -04:00
Vladimir Mandic c03a6928e4 reference models add size and release date info
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-28 21:19:36 -04:00
Vladimir Mandic 2a7e545c09 update qwen layers to min-8bit
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-28 20:50:14 -04:00
Vladimir Mandic 70a2c209b1 cleanup
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-28 20:22:25 -04:00
Vladimir Mandic 78b6124fca Merge pull request #4236 from alerikaisattera/dev
Add model size and release date to reference model list
2025-09-28 18:45:46 -04:00
Vladimir Mandic d01844388d Merge branch 'dev' into dev 2025-09-28 18:45:34 -04:00
Vladimir Mandic 8cc9c23f98 add directml and rocm note to changelog
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-28 18:44:42 -04:00
Vladimir Mandic 813e3c4513 Merge branch 'dev' into dev 2025-09-28 18:33:47 -04:00
Vladimir Mandic c661497b87 linting
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-28 18:09:09 -04:00
Vladimir Mandic eb025eaf31 remove split-attention and add attention slicing option
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-28 18:01:34 -04:00
Disty0 1b45c145e9 SDNQ re-enable dynamic compile 2025-09-28 20:40:24 +03:00
Aleri Kaisattera 9d0d17a54b Add model size and release date to reference model list 2025-09-28 21:44:54 +06:00
Disty0 6f2145fa57 revert offload_buffers 2025-09-28 16:47:31 +03:00