minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 13 Packages Projects Releases Wiki Activity

[CI] Fix stage-b-test-1-gpu-large (0) timeout by reordering LoRA tests and using tokenizer from cache (#22292)

Browse Source 
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Alex Nails
2026-04-07 20:00:44 -07:00
committed by GitHub
co-authored by Claude Opus 4.6
parent 86e4542f35
commit 493ec91cbe
2 changed files with 19 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/registered/perf/test_bench_serving_1gpu_part1.py
+4 -4
View File
@@ -141,7 +141,7 @@ class TestBenchServing1GPUPart1(CustomTestCase):
self.assertLess(res["median_ttft_ms"], 86)
self.assertLess(res["median_itl_ms"], 10)
def test_lora_online_latency(self):
def test_online_lora_latency(self):
if is_in_amd_ci():
pass
@@ -149,14 +149,14 @@ class TestBenchServing1GPUPart1(CustomTestCase):
if is_in_ci():
write_github_step_summary(
f"### test_lora_online_latency\n"
f"### test_online_lora_latency\n"
f"median_e2e_latency_ms: {res['median_e2e_latency_ms']:.2f} ms\n"
f"median_ttft_ms: {res['median_ttft_ms']:.2f} ms\n"
)
self.assertLess(res["median_e2e_latency_ms"], 2400)
self.assertLess(res["median_ttft_ms"], 58)
def test_lora_online_latency_with_concurrent_adapter_updates(self):
def test_online_lora_latency_with_concurrent_adapter_updates(self):
if is_in_amd_ci():
pass
@@ -164,7 +164,7 @@ class TestBenchServing1GPUPart1(CustomTestCase):
if is_in_ci():
write_github_step_summary(
f"### test_lora_online_latency\n"
f"### test_online_lora_latency_with_concurrent_adapter_updates\n"
f"median_e2e_latency_ms: {res['median_e2e_latency_ms']:.2f} ms\n"
f"median_ttft_ms: {res['median_ttft_ms']:.2f} ms\n"
)