8cbbf0be6c
Merge branch 'master' into worksplit-multigpu
2025-10-13 21:53:14 -07:00
c8674bc6e9
Enable RDNA4 pytorch attention on ROCm 7.0 and up. ( #10332 )
2025-10-13 21:19:03 -04:00
a125cd84b0
Improve AMD performance. ( #10302 )
...
I honestly have no idea why this improves things but it does.
2025-10-12 00:28:01 -04:00
c2115a4bac
Merge branch 'master' into worksplit-multigpu
2025-09-24 23:45:26 -07:00
c8d2117f02
Fix memory leak by properly detaching model finalizer ( #9979 )
...
When unloading models in load_models_gpu(), the model finalizer was not
being explicitly detached, leading to a memory leak. This caused
linear memory consumption increase over time as models are repeatedly
loaded and unloaded.
This change prevents orphaned finalizer references from accumulating in
memory during model switching operations.
2025-09-24 22:35:12 -04:00
8d6653fca6
Enable fp8 ops by default on gfx1200 ( #9926 )
2025-09-18 19:50:37 -04:00
efcd8280d6
Merge branch 'master' into worksplit-multigpu
2025-09-11 20:59:47 -07:00
fb763d4333
Fix amd_min_version crash when cpu device. ( #9754 )
2025-09-07 21:16:29 -04:00
bcbd7884e3
Don't enable pytorch attention on AMD if triton isn't available. ( #9747 )
2025-09-07 00:29:38 -04:00
27a0fcccc3
Enable bf16 VAE on RDNA4. ( #9746 )
2025-09-06 23:25:22 -04:00
9e9c129cd0
Merge remote-tracking branch 'origin/master' into worksplit-multigpu
2025-08-29 23:36:19 -07:00
0963493a9c
Support for Qwen Diffsynth Controlnets canny and depth. ( #9465 )
...
These are not real controlnets but actually a patch on the model so they
will be treated as such.
Put them in the models/model_patches/ folder.
Use the new ModelPatchLoader and QwenImageDiffsynthControlnet nodes.
2025-08-20 22:26:37 -04:00
1489399cb5
Merge branch 'master' into worksplit-multigpu
2025-08-13 19:47:08 -07:00
c991a5da65
Fix XPU iGPU regressions ( #9322 )
...
* Change bf16 check and switch non-blocking to off default with option to force to regain speed on certain classes of iGPUs and refactor xpu check.
* Turn non_blocking off by default for xpu.
* Update README.md for Intel GPUs.
2025-08-13 19:13:35 -04:00
962c3c832c
Merge branch 'master' into worksplit-multigpu
2025-08-11 14:09:41 -07:00
5828607ccf
Not sure if AMD actually support fp16 acc but it doesn't crash. ( #9258 )
2025-08-09 12:49:25 -04:00
735bb4bdb1
Users report gfx1201 is buggy on flux with pytorch attention. ( #9244 )
2025-08-08 04:21:00 -04:00
9cca36fa2b
Merge branch 'master' into worksplit-multigpu
2025-07-29 12:47:36 -07:00
7d593baf91
Extra reserved vram on large cards on windows. ( #9093 )
2025-07-29 04:07:45 -04:00
3b90a30178
Merge branch 'master' into worksplit-multigpu-wip
2025-07-27 01:03:25 -07:00
69cb57b342
Print xpu device name. ( #9035 )
2025-07-24 15:06:25 -04:00
0ccc88b03f
Support Iluvatar CoreX ( #8585 )
...
* Support Iluvatar CoreX
Co-authored-by: mingjiang.li <mingjiang.li@iluvatar.com>
2025-07-24 13:57:36 -04:00
d3504e1778
Enable pytorch attention by default for gfx1201 on torch 2.8 ( #9029 )
2025-07-23 19:21:29 -04:00
a86a58c308
Fix xpu function not implemented p2. ( #9027 )
2025-07-23 18:18:20 -04:00
39dda1d40d
Fix xpu function not implemented. ( #9026 )
2025-07-23 18:10:59 -04:00
5ad33787de
Add default device argument. ( #9023 )
2025-07-23 14:20:49 -04:00
255f139863
Add xpu version for async offload and some other things. ( #9004 )
2025-07-22 15:20:09 -04:00
d53479a197
Merge branch 'master' into worksplit-multigpu
2025-07-01 17:33:05 -05:00
a96e65df18
Disable omnigen2 fp16 on older pytorch versions. ( #8672 )
2025-06-26 03:39:09 -04:00
1ae98932f1
Merge branch 'master' into worksplit-multigpu
2025-06-17 04:58:56 -05:00
6e28a46454
Apple most likely is never fixing the fp16 attention bug. ( #8485 )
2025-06-10 13:06:24 -04:00
7f800d04fa
Enable AMD fp8 and pytorch attention on some GPUs. ( #8474 )
...
Information is from the pytorch source code.
2025-06-09 12:50:39 -04:00
97755eed46
Enable fp8 ops by default on gfx1201 ( #8464 )
2025-06-08 14:15:34 -04:00
daf9d25ee2
Cleaner torch version comparisons. ( #8453 )
2025-06-07 10:01:15 -04:00
0336b0ace8
Merge branch 'master' into worksplit-multigpu
2025-06-01 02:39:26 -07:00
704fc78854
Put ROCm version in tuple to make it easier to enable stuff based on it. ( #8348 )
2025-05-30 15:41:02 -04:00
89a84e32d2
Disable initial GPU load when novram is used. ( #8294 )
2025-05-26 16:39:27 -04:00
e5799c4899
Enable pytorch attention by default on AMD gfx1151 ( #8282 )
2025-05-26 04:29:25 -04:00
0b50d4c0db
Add argument to explicitly enable fp8 compute support. ( #8257 )
...
This can be used to test if your current GPU/pytorch version supports fp8 matrix mult in combination with --fast or the fp8_e4m3fn_fast dtype.
2025-05-23 17:43:50 -04:00
9726eac475
Merge branch 'master' into worksplit-multigpu
2025-05-12 19:29:13 -05:00
0a66d4b0af
Per device stream counters for async offload. ( #7873 )
2025-04-29 20:28:52 -04:00
5a50c3c7e5
Fix stream priority to support older pytorch. ( #7856 )
2025-04-28 13:07:21 -04:00
c8cd7ad795
Use stream for casting if enabled. ( #7833 )
2025-04-27 05:38:11 -04:00
0dcc75ca54
Add experimental --async-offload lowvram weight offloading. ( #7820 )
...
This should speed up the lowvram mode a bit. It currently is only enabled when --async-offload is used but it will be enabled by default in the future if there are no problems.
2025-04-26 16:11:21 -04:00
272e8d42c1
Merge branch 'master' into worksplit-multigpu
2025-04-22 22:40:00 -05:00
2d6805ce57
Add option for using fp8_e8m0fnu for model weights. ( #7733 )
...
Seems to break every model I have tried but worth testing?
2025-04-22 06:17:38 -04:00
8be711715c
Make unload_all_models account for all devices
2025-04-19 17:35:54 -05:00
2fa9affcc1
Merge branch 'master' into worksplit-multigpu
2025-04-08 22:52:17 -05:00
2222cf67fd
MLU memory optimization ( #7470 )
...
Co-authored-by: huzhan <huzhan@cambricon.com>
2025-04-02 19:24:04 -04:00
301e26b131
Add option to store TE in bf16 ( #7461 )
2025-04-01 13:48:53 -04:00
Jedrzej Kosinski
comfyanonymous
Guy Niv
DELUXA
Simon Lui
honglyua
BiologicalExplosion
BVH