Jukka Seppänen
55b6a9b11d
Fix thinking handling ( #15611 )
2026-08-14 15:17:18 -04:00
Jukka Seppänen
7fe8a61385
Speedup Gemma4 text generation (CORE-371) ( #15054 )
2026-08-13 21:12:55 -04:00
Barish Ozbay
e01fb4c56b
Add MiniMaxH3AddGuide for anchoring image and audio guides at any frame ( #15439 )
2026-08-13 15:55:36 -04:00
comfyanonymous
03fa4e48ba
Fix minimax music not working on non dynamic vram. ( #15588 )
2026-08-13 15:47:44 -04:00
rattus
ddbaa87528
minimax: early detect qkv vs q,k,v ( #15581 )
...
avoid a commit charge surge on non-dynamic windows due to double linear
creation.
2026-08-13 13:08:08 -04:00
rattus
af3d2153a7
llama: fix non-local x path ( #15580 )
2026-08-13 12:21:26 -04:00
rattus
efd4e951a0
Implement Minimax Music 3 + Core Support for Cuda Graphs ( #15570 )
2026-08-13 12:10:08 -04:00
Alexander Brown
addd479729
Fix Generate Text ignoring thinking=false on Gemma4 E2B/E4B ( #15278 )
2026-08-12 22:44:14 -04:00
Alex Harper
2220d111c8
Query pytorch for aotriton support instead of listing its lib directory ( #15412 )
2026-08-12 21:40:11 -04:00
comfyanonymous
725e6ec606
Support anima tunes with extra blocks. ( #15555 )
2026-08-12 16:22:50 -04:00
comfyanonymous
bd34f338ac
Fix float64 device in ltx diffusion decoder. ( #15516 )
2026-08-12 03:55:08 -04:00
Jukka Seppänen
27bca654eb
Fix KSamplerAdvanced with add_noise disabled on nested latents ( #15447 )
2026-08-11 17:58:00 -04:00
comfyanonymous
024cbc5fc1
Remove potentially problematic process_tokens method. ( #15507 )
2026-08-11 16:45:52 -04:00
comfyanonymous
bbb4b04caa
Don't depend on transformers for mistral and llama tokenizers. ( #15503 )
2026-08-11 15:54:44 -04:00
comfyanonymous
d9f9d2ba12
Fix some clip vision regression. ( #15506 )
2026-08-11 15:54:15 -04:00
comfyanonymous
2a19bbf014
Fix for broken tiled audio decode. ( #15502 )
2026-08-11 14:07:32 -04:00
Alexis Rolland
57ce8e1a27
Add support for LTX 2.5 ( #15499 )
...
---------
Co-authored-by: kijai <40791699+kijai@users.noreply.github.com >
2026-08-11 13:47:39 -04:00
comfyanonymous
62b3c94bd4
Fix peak memory issue with H3. ( #15486 )
2026-08-11 02:09:29 -07:00
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
comfyanonymous
4f3544d131
Make cu130 warning more visible. ( #15463 )
2026-08-10 23:25:01 -04:00
Jukka Seppänen
2a68ce33b4
Optimize MiniMax-H3 VAE ( #15446 )
2026-08-09 14:24:48 -04:00
blepping
cbbc9dab1f
Make a context manager for cast_bias_weight and use it. ( #14750 )
2026-08-08 22:38:34 -04:00
comfyanonymous
cd84f47efe
Make it easier to debug nested tensors. ( #15383 )
2026-08-07 22:14:04 -04:00
Jukka Seppänen
344b43989e
Support asym w4a8_int ( #15308 )
...
* support asym w4a8_int
* Simplify
* Fixes
2026-08-07 08:32:57 -07:00
Jukka Seppänen
93cb5edb98
Fix audio carry to wrappers ( #15390 )
2026-08-07 08:30:21 -07:00
comfyanonymous
2340099d93
Fix full offload on minimax audio vae. ( #15377 )
2026-08-07 00:26:16 -04:00
Jukka Seppänen
a464ac3358
feat: Support Wan-Animate2 (CORE-358) ( #15362 )
2026-08-06 21:08:16 -04:00
comfyanonymous
88fec4b605
Skip creating useless noise in res_multistep sampler. ( #15339 )
2026-08-06 18:17:44 -04:00
Jukka Seppänen
bdcb886a47
Fix sampler issues for audio with minimax, support more samplers. ( #15243 )
2026-08-06 13:36:34 -07:00
endman100
563b98eefb
Fix MiniMax H3 latent noise mask sampling ( #15322 )
2026-08-05 23:47:13 -04:00
Jukka Seppänen
15989f87ca
Speedup LTX and Wan ( #15138 )
2026-08-05 21:15:48 -04:00
Jukka Seppänen
bbda83647d
Support int8_convrot VAE ( #15334 )
2026-08-05 21:12:23 -04:00
rattus
40dbdc1bef
restore SDPA non-cudnn small attention bypass ( #15296 )
...
This is performance critical for ACE step.
2026-08-04 15:25:25 -04:00
rivadart
16e3f3034f
fix(minimax): cast raw parameters to input device in H3 VAEs ( #15268 )
2026-08-03 19:06:12 -04:00
comfyanonymous
e377e26304
Don't pin too much memory on Linux systems with no swap partition. ( #15266 )
2026-08-03 16:29:47 -04:00
Jukka Seppänen
57500fc5bc
feat: Support MiniMax-H3 (CORE-375) ( #15224 )
2026-08-02 22:28:29 -04:00
Oliver Freyermuth
b53e247c94
rename comfy/logging.py to comfy/internal_logging.py ( #15231 )
...
This avoids name collision (circular imports) for external custom nodes,
for which the comfy path is pushed into sys.path so Python's own logging module
is shadowed otherwise.
fixes : #15229
2026-08-02 16:20:27 -04:00
rattus
611f2a4e0f
fix pin registration priority ( #15226 )
...
This priority scheme was broken in the case where you have pin
registration exhaustion while loading a VBAR that gets a big evicition.
The weight would stay in the loaded set but inherit the MRU priority
against other workflow models WRT pin registration which leads to async
offload without pinning.
Fix by universally promiting active pin registration above workflow
pins without concern for the weights/weights-loaded split. This diverges
from the actual budgeting where the split still makes sense.
2026-08-02 08:16:06 -07:00
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
f06a187f50
Handle case where swap memory query fails on windows. ( #15219 )
2026-08-02 01:12:12 -04:00
comfyanonymous
532a16f3b9
Disable gradients on diffusion models. ( #15218 )
2026-08-01 20:15:51 -07:00
Jukka Seppänen
49a7422892
Support latent previews for nested latents ( #15196 )
2026-08-01 19:57:15 -04:00
comfyanonymous
a1c421994c
Expand k, v when attention backend would fall back to math because gqa. ( #15190 )
2026-07-31 15:17:56 -07:00
rattus
7c806288d5
ops: apply the custom placeholder logic to Linux too ( #15181 )
...
Windows has proven this logic works for a long time and there are
corner cases where this materialization actual consumes real RAM
on linux.
Its not as bad as the original windows commit charge surge, but
its still a detectable transient leak. So simplify and unify.
2026-07-31 10:44:09 -07:00
rattus
de5625a64a
Delay dynamic pin cleanup until model destruction ( #15183 )
2026-07-31 10:29:47 -07:00
blepping
831710d257
Don't assume sampler_function has a __name__ attribute in detail logging ( #15179 )
2026-07-31 19:12:17 +03:00
comfyanonymous
f73e8cde88
Fallback to cudnn attention on linux if flash attention doesn't work. ( #15146 )
2026-07-29 18:10:28 -07:00
Barish Ozbay
e651b7bef5
Fix LTXAV crash when sampling without an audio latent ( #15132 )
2026-07-28 20:24:08 -07:00
Jukka Seppänen
c38171ddb9
Support Pruna LTX VAE ( #15129 )
2026-07-28 18:25:55 -04:00
rattus
fbe6d3ca8f
Add configurable DETAIL logging side channel ( #15064 )
2026-07-28 17:31:45 -04:00
