Luca Wehrstedt 2fde495c33 Replace xformers FMHA imports with mslk package ... The xFormers project has migrated its fused multi-head attention (FMHA) implementation to a new standalone package called `mslk` (Meta Superintelligence Labs Kernels). The `xformers` package now re-exports from `mslk` for backward compatibility, but direct dependence on `mslk` is preferred going forward. This commit updates all FMHA import sites to use `mslk.attention.fmha` instead of `xformers.ops`. All user-facing behavior -- CLI arguments, environment variables, log messages, error messages, and documentation -- remains unchanged. What changed: - `import xformers` / `import xformers.ops` replaced with `import mslk` / `import mslk.attention.fmha` in: comfy/model_management.py comfy/ldm/modules/attention.py comfy/ldm/modules/diffusionmodules/model.py comfy/ldm/pixart/blocks.py - Calls to `xformers.ops.memory_efficient_attention(...)` replaced with `mslk.attention.fmha.memory_efficient_attention(...)`. - Version-gating logic for old xformers bugs (0.0.18, 0.0.2x) removed, as those versions predate the mslk migration. - The pip dependency is now `mslk` rather than `xformers`. This migration was prepared by the xFormers team. We have done our best to ensure correctness and preserve all existing behavior, but we welcome feedback from maintainers if anything should be adjusted.		2026-04-23 04:14:12 -07:00
..
audio_encoders	Fix fp16 audio encoder models (#12811)	2026-03-06 18:20:07 -05:00
cldm	Add better error message for common error. (#10846)	2025-11-23 04:55:22 -05:00
comfy_types	fix: use frontend-compatible format for Float gradient_stops (#12789)	2026-03-12 10:14:28 -07:00
extra_samplers	Uni pc sampler now works with audio and video models.	2025-01-18 05:27:58 -05:00
image_encoders	Add Hunyuan 3D 2.1 Support (#8714)	2025-09-04 20:36:20 -04:00
k_diffusion	ace15: Use dynamic_vram friendly trange (#12409)	2026-02-11 14:53:42 -05:00
ldm	Replace xformers FMHA imports with mslk package	2026-04-23 04:14:12 -07:00
sd1_tokenizer	Silence clip tokenizer warning. (#8934)	2025-07-16 14:42:07 -04:00
t2i_adapter	Controlnet refactor.	2024-06-27 18:43:11 -04:00
taesd	Support LTX2 tiny vae (taeltx_2) (#11929)	2026-01-21 23:03:51 -05:00
text_encoders	Use ErnieTEModel_ not ErnieTEModel. (#13431)	2026-04-16 10:11:58 -04:00
weight_adapter	MPDynamic: force load flux img_in weight (Fixes flux1 canny+depth lora crash) (#12446)	2026-02-15 20:30:09 -05:00
cli_args.py	Integrate RAM cache with model RAM management (#13173)	2026-03-27 21:34:16 -04:00
clip_config_bigg.json	Fix potential issue with non clip text embeddings.	2024-07-30 14:41:13 -04:00
clip_model.py	Support the siglip 2 naflex model as a clip vision model. (#11831)	2026-01-12 17:05:54 -05:00
clip_vision_config_g.json	Add support for clip g vision model to CLIPVisionLoader.	2023-08-18 11:13:29 -04:00
clip_vision_config_h.json	Add support for unCLIP SD2.x models.	2023-04-01 23:19:15 -04:00
clip_vision_config_vitl_336_llava.json	Support llava clip vision model.	2025-03-06 00:24:43 -05:00
clip_vision_config_vitl_336.json	support clip-vit-large-patch14-336 (#4042)	2024-07-17 13:12:50 -04:00
clip_vision_config_vitl.json	Add support for unCLIP SD2.x models.	2023-04-01 23:19:15 -04:00
clip_vision_siglip2_base_naflex.json	Support the siglip 2 naflex model as a clip vision model. (#11831)	2026-01-12 17:05:54 -05:00
clip_vision_siglip_384.json	Support new flux model variants.	2024-11-21 08:38:23 -05:00
clip_vision_siglip_512.json	Support 512 siglip model.	2025-04-05 07:01:01 -04:00
clip_vision.py	Reduce RAM usage, fix VRAM OOMs, and fix Windows shared memory spilling with adaptive model loading (#11845)	2026-02-01 01:01:11 -05:00
conds.py	Cleanups to the last PR. (#12646)	2026-02-26 01:30:31 -05:00
context_windows.py	Add slice_cond and per-model context window cond resizing (#12645)	2026-03-19 20:42:42 -07:00
controlnet.py	Add working Qwen 2512 ControlNet (Fun ControlNet) support (#12359)	2026-02-13 22:23:52 -05:00
diffusers_convert.py	Remove useless code.	2025-01-24 06:15:54 -05:00
diffusers_load.py	load_unet -> load_diffusion_model with a model_options argument.	2024-08-12 23:20:57 -04:00
float.py	feat: Support mxfp8 (#12907)	2026-03-14 18:36:29 -04:00
gligen.py	Remove some useless code. (#8812)	2025-07-06 07:07:39 -04:00
hooks.py	New Year ruff cleanup. (#11595)	2026-01-01 22:06:14 -05:00
latent_formats.py	Feat: z-image pixel space (model still training atm) (#12709)	2026-03-02 19:43:47 -05:00
lora_convert.py	Use torch RMSNorm for flux models and refactor hunyuan video code. (#12432)	2026-02-13 15:35:13 -05:00
lora.py	Fix text encoder lora loading for wrapped models (#12852)	2026-03-09 16:08:51 -04:00
memory_management.py	Integrate RAM cache with model RAM management (#13173)	2026-03-27 21:34:16 -04:00
model_base.py	Implement Ernie Image model. (#13369)	2026-04-11 22:29:31 -04:00
model_detection.py	Implement Ernie Image model. (#13369)	2026-04-11 22:29:31 -04:00
model_management.py	Replace xformers FMHA imports with mslk package	2026-04-23 04:14:12 -07:00
model_patcher.py	feat: SUPIR model support (CORE-17) (#13250)	2026-04-18 23:02:01 -04:00
model_sampling.py	initial FlowRVS support (#12637)	2026-02-25 23:38:46 -05:00
nested_tensor.py	WIP way to support multi multi dimensional latents. (#10456)	2025-10-23 21:21:14 -04:00
ops.py	Fix OOM regression in _apply() for quantized models during inference (#13372)	2026-04-15 02:10:36 -07:00
options.py	Only parse command line args when main.py is called.	2023-09-13 11:38:20 -04:00
patcher_extension.py	Fix order of inputs nested merge_nested_dicts (#10362)	2025-10-15 16:47:26 -07:00
pinned_memory.py	Integrate RAM cache with model RAM management (#13173)	2026-03-27 21:34:16 -04:00
pixel_space_convert.py	Changes to the previous radiance commit. (#9851)	2025-09-13 18:03:34 -04:00
quant_ops.py	feat: Support mxfp8 (#12907)	2026-03-14 18:36:29 -04:00
rmsnorm.py	Remove code to support RMSNorm on old pytorch. (#12499)	2026-02-16 20:09:24 -05:00
sample.py	Fix fp16 intermediates giving different results. (#13100)	2026-03-21 17:53:25 -04:00
sampler_helpers.py	Disable dynamic_vram when weight hooks applied (#12653)	2026-02-28 16:50:18 -05:00
samplers.py	Fix sampling issue with fp16 intermediates. (#13099)	2026-03-21 17:47:42 -04:00
sd1_clip_config.json	Fix potential issue with non clip text embeddings.	2024-07-30 14:41:13 -04:00
sd1_clip.py	feat: Support Qwen3.5 text generation models (#12771)	2026-03-25 22:48:28 -04:00
sd.py	Support standalone LTXV audio VAEs (#13499)	2026-04-21 10:46:37 -07:00
sdxl_clip.py	Add a T5TokenizerOptions node to set options for the T5 tokenizer. (#7803)	2025-04-25 19:36:00 -04:00
supported_models_base.py	Fix some custom nodes. (#11134)	2025-12-05 18:25:31 -05:00
supported_models.py	Implement Ernie Image model. (#13369)	2026-04-11 22:29:31 -04:00
utils.py	Reduce tiled decode peak memory (#13050)	2026-03-19 13:29:34 -04:00
windows.py	Reduce RAM usage, fix VRAM OOMs, and fix Windows shared memory spilling with adaptive model loading (#11845)	2026-02-01 01:01:11 -05:00