[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
@@ -2,8 +2,6 @@
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
"""Unit tests for QuantizationConfigArgs parsing."""
from unittest.mock import Mock
import pytest
from tests.quantization.utils import quant_config_args, quant_spec
@@ -244,6 +242,4 @@ def test_targets_reject_moe_only_shorthand_for_linear_layer():
)
with pytest.raises(ValueError, match="does not define a QuantSpec"):
config.resolve_quant_method_cls(
Mock(spec=LinearBase), "model.layers.0.self_attn.o_proj"
)
config.resolve_quant_method_cls(LinearBase, "model.layers.0.self_attn.o_proj")