From 8c0f2d40bda1ea942a4f7f12f59b5625b7fcb471 Mon Sep 17 00:00:00 2001 From: Yuwei An Date: Fri, 27 Feb 2026 17:46:24 -0800 Subject: [PATCH] [CI] Nutanix LoRA adapter removed from HuggingFace (#19533) Signed-off-by: Oasis-Git --- test/registered/perf/test_bench_serving_1gpu_part1.py | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/test/registered/perf/test_bench_serving_1gpu_part1.py b/test/registered/perf/test_bench_serving_1gpu_part1.py index 12629c9d1..27cdcf156 100644 --- a/test/registered/perf/test_bench_serving_1gpu_part1.py +++ b/test/registered/perf/test_bench_serving_1gpu_part1.py @@ -141,6 +141,9 @@ class TestBenchServing1GPUPart1(CustomTestCase): self.assertLess(res["median_ttft_ms"], 86) self.assertLess(res["median_itl_ms"], 10) + @unittest.skip( + "Nutanix/Meta-Llama-3.1-8B-Instruct_lora_4_alpha_16 removed from HuggingFace" + ) def test_lora_online_latency(self): if is_in_amd_ci(): pass @@ -156,6 +159,9 @@ class TestBenchServing1GPUPart1(CustomTestCase): self.assertLess(res["median_e2e_latency_ms"], 2400) self.assertLess(res["median_ttft_ms"], 58) + @unittest.skip( + "Nutanix/Meta-Llama-3.1-8B-Instruct_lora_4_alpha_16 removed from HuggingFace" + ) def test_lora_online_latency_with_concurrent_adapter_updates(self): if is_in_amd_ci(): pass