Commit Graph
5342 Commits
Author SHA1 Message Date
Rando717andGitHub 13ba6a8a8d Update zluda.py (cleanup print Triton version)
compacted, without exception, silent if no version string
2025-09-09 19:30:54 +02:00
Rando717andGitHub ce8900fa25 Update zluda.py (gpu_name_to_gfx)
-function changed into list of rules

-correct gfx codes attached to each GPU name

-addressed potential incorrect designation for  RX 6000 S Series, sort priority
2025-09-09 18:51:41 +02:00
patientxandGitHub d2d0e5d53b Update cfz_caching_condition.py 2025-09-09 12:17:52 +03:00
patientxandGitHub a531352603 Merge branch 'comfyanonymous:master' into master 2025-09-09 01:35:58 +03:00
comfyanonymousandGitHub 103a12cb66 Support qwen inpaint controlnet. (#9772) 2025-09-08 17:30:26 -04:00
patientxandGitHub 6f38e729cc Merge branch 'comfyanonymous:master' into master 2025-09-08 22:15:28 +03:00
Rando717andGitHub e7d48450a3 Update zluda.py (removed previously added gfx90c)
'radeon graphics' check is not viable enough
considering 'radeon (tm) graphics' also exists on Vega.

Plus gfx1036 Raphael (Ryzen 7000) is called 'radeon (tm) graphics' , same with Granite Ridge (Ryzen 9000).
2025-09-08 21:10:20 +02:00
contentisandGitHub 97652d26b8 Add explicit casting in apply_rope for Qwen VL (#9759) 2025-09-08 15:08:18 -04:00
Jedrzej KosinskiandGitHub bd1d9bcd5f Add ZeroDivisionError catch for EasyCache logging statement (#9768) 2025-09-08 15:07:04 -04:00
Rando717andGitHub 590f46ab41 Update zluda.py (typo) 2025-09-08 20:31:49 +02:00
Rando717andGitHub 675d6d8f4c Update zluda.py (gfx gpu names)
-expanded GPU gfx names
-added RDNA4, RDNA3.5, ...
-added missing Polaris cards to prevent 'gfx1010' and 'gfx1030' fallback
-kept gfx designation mostly the same, based on available custom lib's for hip57/62

might need some post adjustments
2025-09-08 17:55:29 +02:00
Rando717andGitHub ddb1e3da47 Update zluda.py (typo) 2025-09-08 17:22:41 +02:00
Rando717andGitHub a7336ad630 Update zluda.py (MEM_BUS_WIDTH#2)
Added Vega10/20 cards.
Can't test, no clue if it has effect or just a placebo effect.
2025-09-08 17:19:03 +02:00
Rando717andGitHub 40199a5244 Update zluda.py (print Triton version)
Added check for Triton version string, if it exists.
Could be useful info for troubleshooting reports.
2025-09-08 17:00:40 +02:00
patientxandGitHub b46622ffa5 Merge branch 'comfyanonymous:master' into master 2025-09-08 11:14:04 +03:00
comfyanonymousandGitHub fb763d4333 Fix amd_min_version crash when cpu device. (#9754) 2025-09-07 21:16:29 -04:00
patientxandGitHub 4babd898ac Merge pull request #293 from Rando717/comfyui-n.bat-(zluda-check)
Update comfyui-n.bat (zluda check)
2025-09-08 03:17:05 +03:00
patientxandGitHub e244301057 Merge pull request #294 from Rando717/comfyui.bat-(zluda-check)
Update comfyui.bat (zluda check)
2025-09-07 20:47:34 +03:00
Rando717andGitHub f4207dc90f Update comfyui.bat (zluda check)
A simple check for zluda.exe and nccl.dll
With hint about AV false positive nccl.dll block.
2025-09-07 17:34:44 +02:00
Rando717andGitHub bb3b73f947 Update comfyui-n.bat (zluda check)
A simple check for zluda.exe and nccl.dll
With hint about AV false positive nccl.dll block.
2025-09-07 17:28:36 +02:00
patientxandGitHub 9417753a6c Merge branch 'comfyanonymous:master' into master 2025-09-07 13:16:57 +03:00
comfyanonymousandGitHub bcbd7884e3 Don't enable pytorch attention on AMD if triton isn't available. (#9747) 2025-09-07 00:29:38 -04:00
comfyanonymousandGitHub 27a0fcccc3 Enable bf16 VAE on RDNA4. (#9746) 2025-09-06 23:25:22 -04:00
patientxandGitHub 2152c91f96 Merge pull request #292 from jeremymeyers/patch-4
Update README.md
2025-09-06 16:36:40 +03:00
Jeremy MeyersandGitHub acce7ca1aa Update README.md
fixed link to cudnn workflow
2025-09-06 09:33:55 -04:00
patientxandGitHub afbcd5d57e Merge branch 'comfyanonymous:master' into master 2025-09-06 11:51:33 +03:00
comfyanonymousandGitHub ea6cdd2631 Print all fast options in --help (#9737) 2025-09-06 01:05:05 -04:00
patientxandGitHub 3ca065a755 fix 2025-09-05 23:11:57 +03:00
patientxandGitHub 0488fe3748 rmsnorm patch second try 2025-09-05 23:10:27 +03:00
patientxandGitHub 8966009181 added rmsnorm patch for torch's older than 2.4 2025-09-05 22:43:39 +03:00
patientxandGitHub f9d7fcb696 Merge branch 'comfyanonymous:master' into master 2025-09-05 22:09:30 +03:00
comfyanonymousandGitHub 2ee7879a0b Fix lowvram issues with hunyuan3d 2.1 (#9735) 2025-09-05 14:57:35 -04:00
Arjan SinghandGitHub 3493b9cb1f fix: add cache headers for images (#9560) 2025-09-05 14:32:25 -04:00
patientxandGitHub 5f05fe3e1d Update cfz_vae_loader.py 2025-09-05 17:40:40 +03:00
patientxandGitHub 79f734309b Update cfz_caching_condition.py 2025-09-05 17:14:59 +03:00
patientxandGitHub 73774a5fac Update __init__.py 2025-09-05 17:13:02 +03:00
patientxandGitHub c7c7269f48 Merge branch 'comfyanonymous:master' into master 2025-09-05 17:11:07 +03:00
comfyanonymousandGitHub c9ebe70072 Some changes to the previous hunyuan PR. (#9725) 2025-09-04 20:39:02 -04:00
Yousef R. GamaleldinandGitHub 261421e218 Add Hunyuan 3D 2.1 Support (#8714) 2025-09-04 20:36:20 -04:00
guillandGitHub a9f1bb10a5 Fix progress update crossover between users (#9706)
* Fix showing progress from other sessions

Because `client_id` was missing from ths `progress_state` message, it
was being sent to all connected sessions. This technically meant that if
someone had a graph with the same nodes, they would see the progress
updates for others.

Also added a test to prevent reoccurance and moved the tests around to
make CI easier to hook up.

* Fix CI issues related to timing-sensitive tests
2025-09-04 19:13:28 -04:00
patientxandGitHub d79e93a0a9 Merge branch 'comfyanonymous:master' into master 2025-09-04 12:41:48 +03:00
comfyanonymous b0338e930b ComfyUI 0.3.57 v0.3.57 2025-09-04 02:15:57 -04:00
ComfyUI WikiandGitHub b71f9bcb71 Update template to 0.1.75 (#9711) 2025-09-04 02:14:02 -04:00
comfyanonymousandGitHub 72855db715 Fix potential rope issue. (#9710) 2025-09-03 22:20:13 -04:00
Alexander PiskunandGitHub f48d05a2d1 convert AlignYourStepsScheduler node to V3 schema (#9226) 2025-09-03 21:21:38 -04:00
patientxandGitHub 577eeaefe6 Merge branch 'comfyanonymous:master' into master 2025-09-04 02:57:38 +03:00
comfyanonymousandGitHub 4368d8f87f Update comment in api example. (#9708) 2025-09-03 18:43:29 -04:00
Alexander PiskunandGitHub 22da0a83e9 [V3] convert Runway API nodes to the V3 schema (#9487)
* convert RunAway API nodes to the V3 schema

* fixed small typo

* fix: add tooltip for "seed" input
2025-09-03 16:18:27 -04:00
Alexander PiskunandGitHub 50333f1715 api nodes(Ideogram): add Ideogram Character (#9616)
* api nodes(Ideogram): add Ideogram Character

* rename renderingSpeed default value from 'balanced' to 'default'
2025-09-03 16:17:37 -04:00
Alexander PiskunandGitHub 26d5b86da8 feat(api-nodes): add ByteDance Image nodes (#9477) 2025-09-03 16:17:07 -04:00