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

[CI] Key scheduled CUDA suites by runner_config instead of hand-written jobs (#34186)

Browse Source
This commit is contained in:
Liangsheng Yin
2026-08-09 16:44:53 -07:00
committed by GitHub
parent 4a5d7d3c67
commit 7c90840bad
94 changed files with 531 additions and 869 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/registered/kernels/ops/diffusion/test_qknorm_rope.py
+1 -1
View File
@@ -10,7 +10,7 @@ from sglang.test.ci.ci_register import register_cuda_ci
register_cuda_ci(est_time=44, stage="base-b-kernel-unit", runner_config="1-gpu-large")
# Nightly is not redundant here: it sets SGLANG_JIT_KERNEL_RUN_FULL_TESTS=1 to expand get_ci_test_range sweeps.
register_cuda_ci(est_time=176, suite="nightly-kernel-1-gpu", nightly=True)
register_cuda_ci(est_time=220, stage="nightly", runner_config="1-gpu-large")
DEVICE = "cuda"
DTYPE = torch.bfloat16
test/registered/kernels/ops/diffusion/test_qwen_image_modulation.py
+1 -1
View File
@@ -14,7 +14,7 @@ from sglang.test.ci.ci_register import register_amd_ci, register_cuda_ci
register_cuda_ci(est_time=15, stage="base-b-kernel-unit", runner_config="1-gpu-large")
# Nightly is not redundant here: it sets SGLANG_JIT_KERNEL_RUN_FULL_TESTS=1 to expand get_ci_test_range sweeps.
register_cuda_ci(est_time=120, suite="nightly-kernel-1-gpu", nightly=True)
register_cuda_ci(est_time=30, stage="nightly", runner_config="1-gpu-large")
register_amd_ci(est_time=30, suite="nightly-amd-kernel-1-gpu", nightly=True)
DEVICE = "cuda"
test/registered/kernels/ops/diffusion/test_timestep_embedding.py
+1 -1
View File
@@ -18,7 +18,7 @@ from sglang.test.ci.ci_register import register_cuda_ci
register_cuda_ci(est_time=16, stage="base-b-kernel-unit", runner_config="1-gpu-large")
# Nightly is not redundant here: it sets SGLANG_JIT_KERNEL_RUN_FULL_TESTS=1 to expand get_ci_test_range sweeps.
register_cuda_ci(est_time=120, suite="nightly-kernel-1-gpu", nightly=True)
register_cuda_ci(est_time=20, stage="nightly", runner_config="1-gpu-large")
CORRECTNESS_BATCH_SIZES = get_ci_test_range(
[1, 2, 8, 128, 256, 512, 1536, 2048, 4096, 11008, 16384],
test/registered/kernels/ops/diffusion/test_varlen_pack_pad.py
+1 -1
View File
@@ -17,7 +17,7 @@ from sglang.test.ci.ci_register import register_amd_ci, register_cuda_ci
register_cuda_ci(est_time=10, stage="base-b-kernel-unit", runner_config="1-gpu-large")
# Nightly is not redundant here: it sets SGLANG_JIT_KERNEL_RUN_FULL_TESTS=1 to expand get_ci_test_range sweeps.
register_cuda_ci(est_time=60, suite="nightly-kernel-1-gpu", nightly=True)
register_cuda_ci(est_time=20, stage="nightly", runner_config="1-gpu-large")
register_amd_ci(est_time=15, suite="nightly-amd-kernel-1-gpu", nightly=True)
DEVICE = "cuda"
test/registered/kernels/ops/diffusion/test_varlen_uspattn_equivalence.py
+1 -1
View File
@@ -31,7 +31,7 @@ from sglang.test.ci.ci_register import register_cuda_ci
register_cuda_ci(est_time=15, stage="base-b-kernel-unit", runner_config="1-gpu-large")
# Nightly is not redundant here: it sets SGLANG_JIT_KERNEL_RUN_FULL_TESTS=1 to expand get_ci_test_range sweeps.
register_cuda_ci(est_time=60, suite="nightly-kernel-1-gpu", nightly=True)
register_cuda_ci(est_time=20, stage="nightly", runner_config="1-gpu-large")
DEVICE = "cuda"
DTYPES = get_ci_test_range([torch.bfloat16, torch.float16], [torch.bfloat16])