[CI] remove itl testing due to unstable networking (#19904)
This commit is contained in:
@@ -125,23 +125,6 @@ class TestDisaggregationDPAttentionRoundRobin(TestDisaggregationDPAttention):
|
|||||||
self.assertLess(result["mean_tpot_ms"], 20)
|
self.assertLess(result["mean_tpot_ms"], 20)
|
||||||
self.assertEqual(result["completed"], 1000)
|
self.assertEqual(result["completed"], 1000)
|
||||||
|
|
||||||
def test_bench_serving_itl(self):
|
|
||||||
num_prompts = 512
|
|
||||||
args = get_benchmark_args(
|
|
||||||
base_url=f"http://{self.base_host}:{self.lb_port}",
|
|
||||||
dataset_name="random",
|
|
||||||
tokenizer=self.model,
|
|
||||||
num_prompts=num_prompts,
|
|
||||||
random_input_len=512,
|
|
||||||
random_output_len=64,
|
|
||||||
request_rate=float("inf"),
|
|
||||||
max_concurrency=64,
|
|
||||||
)
|
|
||||||
result = run_benchmark(args)
|
|
||||||
|
|
||||||
self.assertEqual(result["completed"], num_prompts)
|
|
||||||
self.assertLess(result["p99_itl_ms"], 20)
|
|
||||||
|
|
||||||
|
|
||||||
@unittest.skip(
|
@unittest.skip(
|
||||||
"Skip this test until new testing logic in mini-lb has been updated in docker image."
|
"Skip this test until new testing logic in mini-lb has been updated in docker image."
|
||||||
|
|||||||
Reference in New Issue
Block a user