Add SGLang CUDA crash API logging inspired by FlashInfer (#20910)

python/sglang/jit_kernel/awq_marlin_repack.py

@@ -4,6 +4,7 @@ from typing import TYPE_CHECKING
 
 import torch
 
+from sglang.jit_kernel.debug_utils import maybe_wrap_jit_kernel_debug
 from sglang.jit_kernel.utils import cache_once, load_jit
 
 if TYPE_CHECKING:
@@ -19,6 +20,7 @@ def _jit_awq_marlin_repack_module() -> Module:
     )
 
 
+@maybe_wrap_jit_kernel_debug
 def awq_marlin_repack(
     b_q_weight: torch.Tensor,
     size_k: int,
@@ -37,6 +39,7 @@ def awq_marlin_repack(
     return out
 
 
+@maybe_wrap_jit_kernel_debug
 def awq_marlin_moe_repack(
     b_q_weight: torch.Tensor,
     perm: torch.Tensor,