[CI] Register missing jit_kernel test files

python/sglang/jit_kernel/benchmark/bench_cast.py

@@ -9,6 +9,9 @@
     run_benchmark,
 )
 from sglang.jit_kernel.cast import downcast_fp8 as downcast_fp8_jit
+from sglang.test.ci.ci_register import register_cuda_ci
+
+register_cuda_ci(est_time=10, suite="stage-b-kernel-benchmark-1-gpu-large")
 
 DEVICE = DEFAULT_DEVICE
 DTYPE = torch.bfloat16

python/sglang/jit_kernel/benchmark/bench_fused_qknorm_rope.py

@@ -18,6 +18,9 @@
 from sglang.jit_kernel.fused_qknorm_rope import (
     fused_qk_norm_rope as fused_qk_norm_rope_jit,
 )
+from sglang.test.ci.ci_register import register_cuda_ci
+
+register_cuda_ci(est_time=6, suite="stage-b-kernel-benchmark-1-gpu-large")
 
 try:
     from sgl_kernel import fused_qk_norm_rope as fused_qk_norm_rope_aot

python/sglang/jit_kernel/tests/test_cast.py

@@ -2,6 +2,10 @@
 import torch
 
 from sglang.jit_kernel.cast import downcast_fp8
+from sglang.test.ci.ci_register import register_cuda_ci
+
+register_cuda_ci(est_time=15, suite="stage-b-kernel-unit-1-gpu-large")
+register_cuda_ci(est_time=120, suite="nightly-kernel-1-gpu", nightly=True)
 
 DTYPES = [torch.bfloat16, torch.float16]
 

python/sglang/jit_kernel/tests/test_fused_qknorm_rope.py

@@ -9,6 +9,10 @@
 import torch
 
 from sglang.jit_kernel.fused_qknorm_rope import fused_qk_norm_rope
+from sglang.test.ci.ci_register import register_cuda_ci
+
+register_cuda_ci(est_time=35, suite="stage-b-kernel-unit-1-gpu-large")
+register_cuda_ci(est_time=256, suite="nightly-kernel-1-gpu", nightly=True)
 
 try:
     from sgl_kernel import fused_qk_norm_rope as fused_qk_norm_rope_aot