Jedrzej Kosinski
b326a544d5
Merge branch 'master' into worksplit-multigpu
2025-10-15 17:33:02 -07:00
comfyanonymous
1c10b33f9b
gfx942 doesn't support fp8 operations. ( #10348 )
2025-10-15 00:21:11 -04:00
Jedrzej Kosinski
8cbbf0be6c
Merge branch 'master' into worksplit-multigpu
2025-10-13 21:53:14 -07:00
comfyanonymous
c8674bc6e9
Enable RDNA4 pytorch attention on ROCm 7.0 and up. ( #10332 )
2025-10-13 21:19:03 -04:00
comfyanonymous
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
Jedrzej Kosinski
c2115a4bac
Merge branch 'master' into worksplit-multigpu
2025-09-24 23:45:26 -07:00
Guy Niv
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
DELUXA
8d6653fca6
Enable fp8 ops by default on gfx1200 ( #9926 )
2025-09-18 19:50:37 -04:00
Jedrzej Kosinski
efcd8280d6
Merge branch 'master' into worksplit-multigpu
2025-09-11 20:59:47 -07:00
comfyanonymous
fb763d4333
Fix amd_min_version crash when cpu device. ( #9754 )
2025-09-07 21:16:29 -04:00
comfyanonymous
bcbd7884e3
Don't enable pytorch attention on AMD if triton isn't available. ( #9747 )
2025-09-07 00:29:38 -04:00
comfyanonymous
27a0fcccc3
Enable bf16 VAE on RDNA4. ( #9746 )
2025-09-06 23:25:22 -04:00
Jedrzej Kosinski
9e9c129cd0
Merge remote-tracking branch 'origin/master' into worksplit-multigpu
2025-08-29 23:36:19 -07:00
comfyanonymous
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
Jedrzej Kosinski
1489399cb5
Merge branch 'master' into worksplit-multigpu
2025-08-13 19:47:08 -07:00
Simon Lui
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
Jedrzej Kosinski
962c3c832c
Merge branch 'master' into worksplit-multigpu
2025-08-11 14:09:41 -07:00
comfyanonymous
5828607ccf
Not sure if AMD actually support fp16 acc but it doesn't crash. ( #9258 )
2025-08-09 12:49:25 -04:00
comfyanonymous
735bb4bdb1
Users report gfx1201 is buggy on flux with pytorch attention. ( #9244 )
2025-08-08 04:21:00 -04:00
Jedrzej Kosinski
9cca36fa2b
Merge branch 'master' into worksplit-multigpu
2025-07-29 12:47:36 -07:00
comfyanonymous
7d593baf91
Extra reserved vram on large cards on windows. ( #9093 )
2025-07-29 04:07:45 -04:00
Jedrzej Kosinski
3b90a30178
Merge branch 'master' into worksplit-multigpu-wip
2025-07-27 01:03:25 -07:00
comfyanonymous
69cb57b342
Print xpu device name. ( #9035 )
2025-07-24 15:06:25 -04:00
honglyua
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
comfyanonymous
d3504e1778
Enable pytorch attention by default for gfx1201 on torch 2.8 ( #9029 )
2025-07-23 19:21:29 -04:00
comfyanonymous
a86a58c308
Fix xpu function not implemented p2. ( #9027 )
2025-07-23 18:18:20 -04:00
comfyanonymous
39dda1d40d
Fix xpu function not implemented. ( #9026 )
2025-07-23 18:10:59 -04:00
comfyanonymous
5ad33787de
Add default device argument. ( #9023 )
2025-07-23 14:20:49 -04:00
Simon Lui
255f139863
Add xpu version for async offload and some other things. ( #9004 )
2025-07-22 15:20:09 -04:00
Jedrzej Kosinski
d53479a197
Merge branch 'master' into worksplit-multigpu
2025-07-01 17:33:05 -05:00
comfyanonymous
a96e65df18
Disable omnigen2 fp16 on older pytorch versions. ( #8672 )
2025-06-26 03:39:09 -04:00
Jedrzej Kosinski
1ae98932f1
Merge branch 'master' into worksplit-multigpu
2025-06-17 04:58:56 -05:00
comfyanonymous
6e28a46454
Apple most likely is never fixing the fp16 attention bug. ( #8485 )
2025-06-10 13:06:24 -04:00
comfyanonymous
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
comfyanonymous
97755eed46
Enable fp8 ops by default on gfx1201 ( #8464 )
2025-06-08 14:15:34 -04:00
comfyanonymous
daf9d25ee2
Cleaner torch version comparisons. ( #8453 )
2025-06-07 10:01:15 -04:00
kosinkadink1@gmail.com
0336b0ace8
Merge branch 'master' into worksplit-multigpu
2025-06-01 02:39:26 -07:00
comfyanonymous
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
comfyanonymous
89a84e32d2
Disable initial GPU load when novram is used. ( #8294 )
2025-05-26 16:39:27 -04:00
comfyanonymous
e5799c4899
Enable pytorch attention by default on AMD gfx1151 ( #8282 )
2025-05-26 04:29:25 -04:00
comfyanonymous
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
Jedrzej Kosinski
9726eac475
Merge branch 'master' into worksplit-multigpu
2025-05-12 19:29:13 -05:00
comfyanonymous
0a66d4b0af
Per device stream counters for async offload. ( #7873 )
2025-04-29 20:28:52 -04:00
comfyanonymous
5a50c3c7e5
Fix stream priority to support older pytorch. ( #7856 )
2025-04-28 13:07:21 -04:00
comfyanonymous
c8cd7ad795
Use stream for casting if enabled. ( #7833 )
2025-04-27 05:38:11 -04:00
comfyanonymous
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
Jedrzej Kosinski
272e8d42c1
Merge branch 'master' into worksplit-multigpu
2025-04-22 22:40:00 -05:00
comfyanonymous
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
Jedrzej Kosinski
8be711715c
Make unload_all_models account for all devices
2025-04-19 17:35:54 -05:00
Jedrzej Kosinski
2fa9affcc1
Merge branch 'master' into worksplit-multigpu
2025-04-08 22:52:17 -05:00
