The diffusion loader treated any quant config without the MXFP8/
is_checkpoint_quantized markers as online quantization: it loaded every
component on the accelerator before offloading, so serving the int8
weight-only compressed-tensors artifact OOM'd at model construction
(encoder 17 GiB + VAE + packed DiT skeleton > 24 GiB). compressed-tensors
is always a serialized format with no on-load quantization pass — detect
it (through component wrappers too) and load on the host, round-tripping
each quantized module through the accelerator only for the post-load
Marlin repack, which has no CPU path.
quantize_dit_int8wo.py builds the offline W8A16 artifact (per-channel
symmetric int8, pack-quantized via compressed-tensors' own packer,
per-component config wrapper so encoder/VAE stay BF16, digest manifest);
serve.sh/probe.py/gate.py/psnr.py adapt the issue-2 kit for the
structure-gated capacity matrix (1-4 refs x seeds 2301-2304).
_normalize_method_name canonicalizes dashes to underscores for _OVERRIDES
lookup, but vLLM's QUANTIZATION_METHODS keeps historical spellings
('compressed-tensors'), so both --quantization compressed-tensors and
checkpoint auto-detection raised 'Unknown quantization method'. Resolve
the normalized name back to the registry spelling, and fall back to
from_config for registry configs whose __init__ does not take the
serialized schema (compressed-tensors config_groups/format/ignore).
admin