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

[AMD] Fix CI - unit-test-backend-1-gpu-amd-mi35x and unit-test-backend-2-gpu-amd, stage-b-test-small-1-gpu-amd (#16675)

Browse Source 
Co-authored-by: Bingxu Chen <bingxche@amd.com>
This commit is contained in:
YC Tseng
2026-01-08 10:16:27 -08:00
committed by GitHub
co-authored by Bingxu Chen
parent fbc24886dd
commit 4e999404c3
60 changed files with 106 additions and 143 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/registered/attention/test_create_kvindices.py
+1 -1
View File
@@ -9,7 +9,7 @@ from sglang.test.test_utils import CustomTestCase
# Triton kernel unit test for KV indices creation
register_cuda_ci(est_time=10, suite="stage-b-test-small-1-gpu")
register_amd_ci(est_time=10, suite="stage-b-test-small-1-gpu")
register_amd_ci(est_time=10, suite="stage-b-test-small-1-gpu-amd")
class TestCreateKvIndices(CustomTestCase):
test/registered/attention/test_radix_attention.py
+1 -1
View File
@@ -15,7 +15,7 @@ from sglang.test.test_utils import (
# RadixAttention server integration tests
register_cuda_ci(est_time=100, suite="stage-b-test-small-1-gpu")
register_amd_ci(est_time=100, suite="stage-b-test-small-1-gpu")
register_amd_ci(est_time=100, suite="stage-b-test-small-1-gpu-amd")
class TestRadixCacheFCFS(CustomTestCase):
test/registered/attention/test_swa_unittest.py
+1 -1
View File
@@ -10,7 +10,7 @@ from sglang.srt.mem_cache.swa_radix_cache import SWARadixCache
from sglang.test.ci.ci_register import register_amd_ci, register_cuda_ci
register_cuda_ci(est_time=8, suite="stage-b-test-small-1-gpu")
register_amd_ci(est_time=10, suite="stage-b-test-small-1-gpu")
register_amd_ci(est_time=10, suite="stage-b-test-small-1-gpu-amd")
class TestSWA(unittest.TestCase):
test/registered/attention/test_torch_native_attention_backend.py
+1 -1
View File
@@ -19,7 +19,7 @@ from sglang.test.test_utils import (
# Torch native attention backend integration test with MMLU eval
register_cuda_ci(est_time=150, suite="stage-b-test-small-1-gpu")
register_amd_ci(est_time=150, suite="stage-b-test-small-1-gpu")
register_amd_ci(est_time=150, suite="stage-b-test-small-1-gpu-amd")
class TestTorchNativeAttnBackend(CustomTestCase):
test/registered/attention/test_triton_attention_backend.py
+1 -1
View File
@@ -21,7 +21,7 @@ from sglang.test.test_utils import (
# Triton attention backend integration test with latency benchmark and MMLU eval
register_cuda_ci(est_time=200, suite="stage-b-test-small-1-gpu")
register_amd_ci(est_time=1110, suite="stage-b-test-small-1-gpu")
register_amd_ci(est_time=1110, suite="stage-b-test-small-1-gpu-amd")
class TestTritonAttnBackend(CustomTestCase):
test/registered/attention/test_triton_attention_kernels.py
+1 -1
View File
@@ -26,7 +26,7 @@ from sglang.test.test_utils import CustomTestCase
register_cuda_ci(est_time=30, suite="stage-b-test-small-1-gpu")
register_amd_ci(
est_time=30,
suite="stage-b-test-small-1-gpu",
suite="stage-b-test-small-1-gpu-amd",
disabled="test was never enabled for AMD CI, needs validation",
)
test/registered/attention/test_triton_sliding_window.py
+1 -1
View File
@@ -16,7 +16,7 @@ from sglang.test.test_utils import (
# Sliding window attention with Triton backend (Gemma-3 model)
register_cuda_ci(est_time=100, suite="stage-b-test-small-1-gpu")
register_amd_ci(est_time=100, suite="stage-b-test-small-1-gpu")
register_amd_ci(est_time=100, suite="stage-b-test-small-1-gpu-amd")
class TestSlidingWindowAttentionTriton(CustomTestCase):