fix(quantization): Fix AWQ dequantize on Intel XPU and refactor AutoAWQ config (#42727)
Signed-off-by: Alex <alex.tech.lab@outlook.com> Signed-off-by: AlexHuang <jihuihuang@tencent.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Kunshang Ji <kunshang.ji@intel.com> Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
This commit is contained in:
co-authored by
Claude
Kunshang Ji
mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
parent
351c72d6e5
commit
8d4f54966c
@@ -645,11 +645,11 @@ def test_resolve_awq_moe_uses_marlin_when_supported(monkeypatch) -> None:
|
||||
lambda *args, **kwargs: True,
|
||||
)
|
||||
monkeypatch.setattr(
|
||||
"vllm.model_executor.layers.quantization.awq_marlin.verify_marlin_supported",
|
||||
"vllm.model_executor.layers.quantization.auto_awq.verify_marlin_supported",
|
||||
lambda *args, **kwargs: None,
|
||||
)
|
||||
monkeypatch.setattr(
|
||||
"vllm.model_executor.layers.quantization.awq_marlin.AWQMarlinMoEMethod",
|
||||
"vllm.model_executor.layers.quantization.auto_awq.AutoAWQMoEMethod",
|
||||
DummyMethod,
|
||||
)
|
||||
|
||||
|
||||
Reference in New Issue
Block a user