mirror of
https://github.com/comfyanonymous/ComfyUI.git
synced 2026-06-21 15:29:32 +08:00
3ddcc095ed
Wires comfy-kitchen's TensorCoreAWQW4A16Layout (introduced on
feat/awq-w4a16-modulation) into ComfyUI's MixedPrecisionOps so checkpoints
that tag modulation linears with comfy_quant.format = "awq_w4a16" get
their (qweight, weight_scale, weight_zero) loaded into the kitchen layout
class instead of being dequantized to bf16 plain Linear at conversion time.
quant_ops.py:
- detect TensorCoreAWQW4A16Layout availability and stub it out for the
no-kitchen fallback (mirrors the SVDQuant W4A4 pattern)
- register the layout class + add "awq_w4a16" to QUANT_ALGOS
(storage_t = int8 packed uint4, parameters = {weight_scale, weight_zero},
default group_size = 64)
ops.py: add the awq_w4a16 branch in MixedPrecisionOps.Linear._load_from_state_dict
that constructs Params(scale, zeros, group_size, ...) and wraps qweight
into a QuantizedTensor — F.linear then dispatches to ck.gemv_awq_w4a16
via the layout's aten handlers.
Pairs with comfy-kitchen feat/awq-w4a16-modulation. Targets the ~10 GB
inflation in Qwen-Image-Edit kitchen-native checkpoints, where the
modulation linears (img_mod.1 / txt_mod.1) currently dominate disk + VRAM
because they're materialized as plain bf16 Linear during conversion.
|
||
|---|---|---|
| .. | ||
| audio_encoders | ||
| cldm | ||
| comfy_types | ||
| extra_samplers | ||
| image_encoders | ||
| k_diffusion | ||
| ldm | ||
| sd1_tokenizer | ||
| t2i_adapter | ||
| taesd | ||
| text_encoders | ||
| weight_adapter | ||
| cli_args.py | ||
| clip_config_bigg.json | ||
| clip_model.py | ||
| clip_vision_config_g.json | ||
| clip_vision_config_h.json | ||
| clip_vision_config_vitl_336_llava.json | ||
| clip_vision_config_vitl_336.json | ||
| clip_vision_config_vitl.json | ||
| clip_vision_siglip2_base_naflex.json | ||
| clip_vision_siglip_384.json | ||
| clip_vision_siglip_512.json | ||
| clip_vision.py | ||
| conds.py | ||
| context_windows.py | ||
| controlnet.py | ||
| diffusers_convert.py | ||
| diffusers_load.py | ||
| float.py | ||
| gligen.py | ||
| hooks.py | ||
| latent_formats.py | ||
| lora_convert.py | ||
| lora.py | ||
| memory_management.py | ||
| model_base.py | ||
| model_detection.py | ||
| model_management.py | ||
| model_patcher.py | ||
| model_sampling.py | ||
| nested_tensor.py | ||
| ops.py | ||
| options.py | ||
| patcher_extension.py | ||
| pinned_memory.py | ||
| pixel_space_convert.py | ||
| quant_ops.py | ||
| rmsnorm.py | ||
| sample.py | ||
| sampler_helpers.py | ||
| samplers.py | ||
| sd1_clip_config.json | ||
| sd1_clip.py | ||
| sd.py | ||
| sdxl_clip.py | ||
| supported_models_base.py | ||
| supported_models.py | ||
| utils.py | ||
| windows.py | ||