We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 101f75d commit 9dadf9aCopy full SHA for 9dadf9a
tests/compile/test_fusions_e2e.py
@@ -334,6 +334,11 @@ def test_tp2_attn_quant_async_tp(
334
pytest.skip("FlashInfer attn fusion requires Blackwell and flashinfer")
335
if inductor_graph_partition and not is_torch_equal_or_newer("2.9.0.dev"):
336
pytest.skip("Inductor graph partition requires torch>=2.9")
337
+ if inductor_graph_partition and "fp4" in model_name.lower():
338
+ pytest.skip(
339
+ "Known bug for fp4 fusion & inductor partition: "
340
+ "https://github.com/vllm-project/vllm/issues/26988"
341
+ )
342
343
custom_ops_list = custom_ops.split(",") if custom_ops else []
344
0 commit comments