[Quantization] Support compressed-tensors MXFP4 MoE with FP8 activations via Mxfp4MoEMethod (#59815)

Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Kevin H. Luu <khluu000@gmail.com>
This commit is contained in:
Misha Goin
2026-10-14 13:33:35 -07:00
committed by GitHub
co-authored by Claude Kevin H. Luu
parent fe98d90a9d
commit 984c242ede
12 changed files with 311 additions and 10 deletions
@@ -59,6 +59,7 @@ def prepare_humming_linear_layer_config(
input_quant_config: dict | None = None,
*,
input_schema: "BaseInputSchema | None" = None,
allow_input_schema_fallback: bool = True,
) -> "LayerConfig":
from vllm.utils.humming import (
BaseInputSchema,
@@ -119,6 +120,7 @@ def prepare_humming_linear_layer_config(
weight_schema=weight_schema,
input_schema=input_schema,
param_dtype=layer.params_dtype,
allow_fallback=allow_input_schema_fallback,
)
for name in ("input_scale", "input_scale_2"):
if name != input_schema.static_tensor_scale_name: