minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

[CPU][CI]: fix a few issues that cause XEON CI failures (#36413)

Browse Source 
Co-authored-by: Zhang, Mingxu <mingxu.zhang@intel.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: MingxuZh <109504044+MingxuZh@users.noreply.github.com>
This commit is contained in:
Xia Weiwen
2026-08-27 13:59:08 +08:00
committed by GitHub
co-authored by Zhang, Mingxu Claude MingxuZh
parent ea48cb04cc
commit b294bd4bc7
3 changed files with 48 additions and 64 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/registered/cpu/test_intel_amx_attention_backend_a.py
+2 -2
View File
@@ -34,7 +34,7 @@ class TestIntelAMXAttnBackend(CustomTestCase):
return DEFAULT_MLA_MODEL_NAME_FOR_TEST
@intel_amx_benchmark(
extra_args=["--batch-size", "4", "--mem-fraction-static", "0.2"],
extra_args=["--batch-size", "4", "--mem-fraction-static", "0.3"],
min_throughput=40,
)
def test_latency_default_model(self):
@@ -84,7 +84,7 @@ class TestDPAttention(CustomTestCase):
"--attention-backend",
"intel_amx",
"--mem-fraction-static",
"0.2",
"0.3",
"--disable-overlap-schedule",
"--tp",
"2",
test/registered/cpu/test_intel_amx_attention_backend_b.py
+2 -2
View File
@@ -20,14 +20,14 @@ register_cpu_ci(est_time=47, suite="base-b-test-cpu")
class TestIntelAMXAttnBackendQuant(CustomTestCase):
@intel_amx_benchmark(
extra_args=["--batch-size", "4", "--mem-fraction-static", "0.2"],
extra_args=["--batch-size", "4", "--mem-fraction-static", "0.3"],
min_throughput=150,
)
def test_latency_fp8_qwen(self):
return DEFAULT_MODEL_NAME_FOR_TEST_QWEN_FP8
@intel_amx_benchmark(
extra_args=["--batch-size", "4", "--mem-fraction-static", "0.2"],
extra_args=["--batch-size", "4", "--mem-fraction-static", "0.3"],
min_throughput=50,
)
def test_latency_fp8_moe_model(self):