diff --git a/python/sglang/test/test_utils.py b/python/sglang/test/test_utils.py index 1c65776bc..5ebbca864 100644 --- a/python/sglang/test/test_utils.py +++ b/python/sglang/test/test_utils.py @@ -2223,6 +2223,12 @@ class ModelLaunchSettings: self.extra_args.append(fixed_arg) +class ModelEvalMetrics: + def __init__(self, accuracy: float, eval_time: float): + self.accuracy = accuracy + self.eval_time = eval_time + + def extract_trace_link_from_bench_one_batch_server_output(output: str) -> str: match = re.search(r"\[Profile\]\((.*?)\)", output) if match: diff --git a/test/registered/backends/test_flashinfer_trtllm_gen_moe_backend.py b/test/registered/backends/test_flashinfer_trtllm_gen_moe_backend.py index 72915e292..0105ba6bc 100644 --- a/test/registered/backends/test_flashinfer_trtllm_gen_moe_backend.py +++ b/test/registered/backends/test_flashinfer_trtllm_gen_moe_backend.py @@ -332,6 +332,14 @@ class TestFlashinferTrtllmGenMoeBackendNvFp4PerTokenActivationRouted( backend = "flashinfer_trtllm_routed" +# Only this class is affected, but the file runs with failfast, so leaving it +# enabled also cuts off the two classes that sort after it. +@unittest.skip( + "flashinfer-ai/flashinfer#4486: on SM100/SM103 the TRTLLM_GEN tile-192 BMM " + "path returns non-finite MoE output from FlashInfer 0.6.16.post4 on, so the " + "first real prefill trips the sampler NaN assert and gsm8k scores 0.0. " + "See #34629 for the package bisect." +) class TestFlashinferTrtllmGenMoeBackendNvFp4Online( FlashinferTrtllmGenMoeBackendNvFp4OnlineBase, CustomTestCase ):