Reverts 6bf533e, 78c9625, 4bacc9c, 993e5e4, ae337b5 and c4d8018 —
gguf_support.py, loaders.py and their tests are byte-identical to
6f04642. Nothing else is touched.
The quantized path loaded fast and gave the sampler a model it could not
run: shape [21504, 5376] against an input of 22848x5376, one 1344-token
unit apart. Expanding at load is slow and works.
Dequantizing produces float32 — four times the width the weight ends up
at. Every tensor was collected before any was cast, so the peak was the
whole checkpoint in float32 plus a copy of each: tens of GB of transient
host allocation on a video model, enough to take the machine down rather
than just the load. ThreadPoolExecutor.map made it worse by submitting
everything at once and buffering results in order.
Now cast-and-release per tensor, with a fixed in-flight window. Peak is
the finished model plus a handful of tensors. Pool capped at 4.
Also prints the path and tensor count before the wait, so a load killed
part way leaves evidence of which backend it chose.
A bare "'dict' object has no attribute 'startswith'" names neither the
step nor the file. Each stage now labels itself in the re-raise. The
ComfyUI-GGUF architecture override is opt-in, not default.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Attention and SLA are applied to a clone of a one-entry weight cache
keyed on file identity + dtypes, so a sparsity change skips the disk.
GGUF dequantization now runs across threads instead of serially.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
A .gguf renamed .safetensors reached the safetensors parser (UTF-8 decode
error); content now decides. ComfyUI-GGUF's loader uses relative imports, so
its directory is mounted as a package instead of loaded file-by-file.
Core lists no .gguf, so the files were invisible. Backend is whichever is
installed: ComfyUI-GGUF keeps weights quantized, the gguf package
dequantizes at load. Family detection reads GGUF containers too.
It is a toggle now, not a value in the list: SLA takes H3's packed self-attention
and the chosen backend takes the text refiner, masked calls and dense-last steps.
When SLA does not take, the chosen backend is still installed on its own.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Picked in the diffusion model loader's attention list, not wired as a node.
Six settings folded under Advanced; offered only where CUDA and Triton run it
and ignored on any model that is not H3. Kernel vendored from LightX2V.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Quantization + a per-model attention backend read from ComfyUI's own registry, so only
installed ones are offered. The LoRA loader now takes its own list and scores wrapper
prefixes against the model's key map, instead of applying a diffusers LoRA as a silent no-op.
digital-garbage