diff --git a/tests/e2e/nightly/single_node/models/test_qwen3_next_w8a8.py b/tests/e2e/nightly/single_node/models/test_qwen3_next_w8a8.py index e066ae19..a08e3fbd 100644 --- a/tests/e2e/nightly/single_node/models/test_qwen3_next_w8a8.py +++ b/tests/e2e/nightly/single_node/models/test_qwen3_next_w8a8.py @@ -78,7 +78,7 @@ async def test_models(model: str) -> None: "--gpu-memory-utilization", "0.65", "--compilation-config", - '{"cudagraph_capture_sizes": [32], "cudagraph_mode":"FULL_DECODE_ONLY"}', + '{"cudagraph_capture_sizes": [32]}', ] request_keyword_args: dict[str, Any] = { **api_keyword_args,