chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 11 Packages Projects Releases Wiki Activity

[CI] Nutanix LoRA adapter removed from HuggingFace (#19533)

Browse Source 
Signed-off-by: Oasis-Git <ayw.sirius19@gmail.com>
This commit is contained in:
Yuwei An
2026-02-27 17:46:24 -08:00
committed by GitHub
parent 5f07ff9271
commit 8c0f2d40bd
1 changed files with 6 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
test/registered/perf/test_bench_serving_1gpu_part1.py
View File

@@ -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