Daxiong (Lin)
86aedfd943
chore: update workflow templates to v0.11.41 ( #15578 )
2026-08-13 12:23:02 -04:00
comfyanonymous
b323a345bb
Update comfy-kitchen package version to 0.2.31 ( #15564 )
2026-08-12 23:01:31 -04:00
Daxiong (Lin)
1108f2ac5e
chore: update workflow templates to v0.11.40 ( #15522 )
2026-08-11 22:24:24 -07:00
Daxiong (Lin)
eb4a7b4fcf
chore: update workflow templates to v0.11.39 ( #15504 )
2026-08-11 15:20:39 -04:00
comfyanonymous
bf4c9a08fc
Implement comfy kitchen attention. ( #15479 )
...
Add a ModelAttentionBackend node to manually select the attention for models in the workflows. Currently supports pytorch attention or comfy kitchen attention.
Add --use-ck-attention to enable comfy kitchen attention as the default attention backend for all models (might break some).
2026-08-10 22:03:08 -07:00
Daxiong (Lin)
5599a05fea
chore: update workflow templates to v0.11.37 ( #15415 )
2026-08-07 19:27:21 -07:00
comfyanonymous
66057c4e59
Update comfy-kitchen package version to 0.2.28 ( #15407 )
2026-08-07 18:25:27 -04:00
Daxiong (Lin)
2f40b7131c
chore: update workflow templates to v0.11.34 ( #15404 )
2026-08-07 13:28:01 -07:00
Comfy Org PR Bot
6db4fa2fcd
Bump comfyui-frontend-package to 1.48.7 ( #15403 )
2026-08-07 11:51:34 -07:00
comfyanonymous
0ab8332bfa
Update comfy-kitchen package version to 0.2.27 ( #15388 )
2026-08-07 03:33:38 -04:00
Comfy Org PR Bot
6f7cd7fcea
Bump comfyui-frontend-package to 1.48.6 ( #15301 )
2026-08-04 19:53:21 -07:00
rattus
ba1d0efc9f
comfy-aimdo 0.4.13 ( #15290 )
...
Comfy-aimdo 0.4.12 increases error logging reliablity to help root
cause os errors in some of the C APIs that are causing issues for
some users.
The log is also unified with python logging, so non-terminal users
see the logs properly.
Aimdo 0.4.13 fixes a bug in async-offload + MRU primary weights
allocation. https://github.com/Comfy-Org/ComfyUI/issues/15284
2026-08-04 21:47:11 -04:00
Daxiong (Lin)
2bbb200dc9
chore: update workflow templates to v0.11.31 ( #15297 )
...
Co-authored-by: Jedrzej Kosinski <kosinkadink1@gmail.com >
2026-08-04 17:29:44 -07:00
Comfy Org PR Bot
14b05228ce
Bump comfyui-frontend-package to 1.47.12 ( #15244 )
...
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2026-08-02 22:03:37 -07:00
Daxiong (Lin)
6eba7739f0
chore: update workflow templates to v0.11.27 ( #15239 )
2026-08-02 19:47:04 -07:00
Daxiong (Lin)
f72b68878e
Update workflow templates to v0.11.26 ( #15228 )
2026-08-02 22:29:02 -04:00
rattus
8084083d4b
comfy-aimdo 0.4.11 ( #15215 )
...
Changes:
Remove sequential scan hint
Prefer NVML pressure on windows
Add async malloc clamp option (unused by comfy so far)
Workaround AMD windows GPU virtual address space leak
The largest change is the NVML pressure, which works around a cuMemGetInfo
drift from actual VRAM in some circumstances.
2026-08-02 06:55:37 -04:00
comfyanonymous
e8e233cdf6
Update comfy-kitchen version to 0.2.26 ( #15208 )
2026-08-01 15:10:39 -04:00
Daxiong (Lin)
0b73ae83a1
chore: update workflow templates to v0.11.23 ( #15187 )
2026-08-01 02:20:55 +08:00
Daxiong (Lin)
b6fe23b4f1
chore: update workflow templates to v0.11.20 ( #15165 )
2026-07-30 19:27:06 -07:00
Comfy Org PR Bot
c20269c1cb
Bump comfyui-frontend-package to 1.47.11 ( #15161 )
2026-07-30 20:05:51 -04:00
comfyanonymous
8352644aa9
comfy-kitchen AMD support. ( #15160 )
2026-07-30 19:53:13 -04:00
comfyanonymous
4f874c5e3a
Update comfy-kitchen to fix flux kv issue. ( #15144 )
2026-07-29 14:10:01 -07:00
comfyanonymous
628cdec592
Update comfy-kitchen package version to 0.2.23 ( #15112 )
2026-07-28 17:01:53 -04:00
Daxiong (Lin)
e8f8c2ff43
chore: update workflow templates to v0.11.19 ( #15123 )
2026-07-29 00:45:57 +08:00
Daxiong (Lin)
093d571b83
chore: update embedded docs to v0.5.9 ( #15092 )
2026-07-27 08:59:14 +08:00
Daxiong (Lin)
c0ca3a5991
chore: update workflow templates to v0.11.17 ( #15059 )
2026-07-24 19:13:09 +08:00
Comfy Org PR Bot
a449f5f987
Bump comfyui-frontend-package to 1.47.10 ( #15045 )
2026-07-23 10:59:00 +02:00
Daxiong (Lin)
54ca9193a3
chore: update workflow templates to v0.11.15 ( #15030 )
2026-07-23 00:49:39 +08:00
Daxiong (Lin)
7774301a7b
chore: update workflow templates to v0.11.12 ( #14986 )
2026-07-18 23:44:22 +08:00
comfyanonymous
4800e78518
More comfy-kitchen int8 optimizations. ( #14980 )
2026-07-18 00:53:15 -04:00
Daxiong (Lin)
1d1099bea0
chore: update workflow templates to v0.11.11 ( #14973 )
2026-07-18 00:53:15 +08:00
comfyanonymous
6a8ff7a929
Various comfy kitchen optimizations and fixes. ( #14963 )
2026-07-16 19:43:12 -07:00
Comfy Org PR Bot
3cd13eb424
Bump comfyui-frontend-package to 1.45.21 ( #14944 )
2026-07-15 01:29:24 -04:00
comfyanonymous
dff0b18fff
Fix int8 performance regression on 16xx series. ( #14941 )
2026-07-14 13:13:08 -07:00
comfyanonymous
80acfcf0fe
More optimized int8 and int4 on turing. ( #14927 )
2026-07-13 13:03:29 -07:00
Daxiong (Lin)
da2608926e
Update workflow templates to v0.11.9 ( #14924 )
2026-07-13 12:15:34 -07:00
Daxiong (Lin)
5bb831a3f5
chore: update embedded docs to v0.5.8 ( #14920 )
2026-07-13 22:13:23 +08:00
comfyanonymous
e2a6e30d89
Fix black image on turing when using int4 models. ( #14864 )
2026-07-09 23:17:06 -04:00
comfyanonymous
73e84d5ec8
Support convrot int4 models. ( #14859 )
...
linear_dtype in comfy_quant metadata can be used to set if the int4 op does
the matrix multiplication in int8 or int4, the default is int4 on GPUs that
support it with fallback to int8 for GPUs that don't.
2026-07-09 18:57:09 -04:00
Daxiong (Lin)
6cc814437f
Update workflow templates to v0.11.6 ( #14834 )
2026-07-08 14:04:57 -07:00
Daxiong (Lin)
b08debceca
chore: update embedded docs to v0.5.7 ( #14783 )
2026-07-06 09:56:09 +08:00
Daxiong (Lin)
a04ebe05c2
chore: update workflow templates to v0.11.2 ( #14741 )
2026-07-03 19:08:11 +08:00
Daxiong (Lin)
6fca64780c
chore: update workflow templates to v0.11.1 ( #14698 )
2026-06-30 14:28:09 -07:00
comfyanonymous
d395813bcd
Fix memory leak related to int8. ( #14697 )
2026-06-30 14:08:59 -07:00
Comfy Org PR Bot
510ed5c384
Bump comfyui-frontend-package to 1.45.20 ( #14684 )
2026-06-30 16:25:03 +08:00
comfyanonymous
7851410511
Better and faster int8 lora applying. ( #14685 )
2026-06-29 21:52:08 -04:00
Daxiong (Lin)
a58473fd9b
chore: update embedded docs to v0.5.6 ( #14668 )
...
Co-authored-by: Alexis Rolland <alexisrolland@hotmail.com >
2026-06-29 17:08:06 +08:00
comfyanonymous
a95e461916
int8 support on turing GPUs. ( #14662 )
2026-06-27 15:53:11 -07:00
pythongosssss
603d891eaf
Update GLSL node to use ANGLE library (CORE-162) ( #13195 )
2026-06-27 08:40:31 +08:00
