[Quantization] Enable shared expert fusion compatibility with online shared_expert quantization (showcase: along Quark MXFP4 routed experts) (#55686)

Signed-off-by: Felix Marty <Felix.Marty@amd.com>
Signed-off-by: fxmarty-amd <felmarty@amd.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: Misha Goin <mgoin64@gmail.com>
This commit is contained in:
fxmarty-amd
2026-10-08 12:04:46 -04:00
committed by GitHub
co-authored by OpenAI Codex Misha Goin
parent e2414ec1db
commit 9f3d70e081
24 changed files with 984 additions and 73 deletions
+2 -3
View File
@@ -2,11 +2,10 @@
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
"""Tests quantization configuration matching utilities."""
from unittest.mock import Mock
import pytest
from vllm.config.quantization import QuantizationConfigArgs
from vllm.model_executor.layers.linear import LinearBase
from vllm.model_executor.layers.quantization.compressed_tensors.utils import (
should_ignore_layer,
)
@@ -58,7 +57,7 @@ def test_online_ignore_supports_fnmatch_patterns():
)
with pytest.raises(ValueError, match="matches both quantization_config.ignore"):
config.resolve_quant_method_cls(Mock(), layer_name)
config.resolve_quant_method_cls(LinearBase, layer_name)
@pytest.mark.parametrize(