move all get_stream in sgl_kernel to c++ to reduce the launch overhead (#12521)

2025-11-02 13:15:05 -08:00
parent c9db79117f
commit 20315697f4
20 changed files with 61 additions and 94 deletions
@@ -52,8 +52,8 @@ make build
   ```cpp
   // We need def with schema here for torch.compile
   m.def(
-    "bmm_fp8(Tensor A, Tensor B, Tensor! D, Tensor A_scale, Tensor B_scale, Tensor workspace_buffer, int "
-    "cublas_handle, int cuda_stream) -> ()");
+    "bmm_fp8(Tensor A, Tensor B, Tensor! D, Tensor A_scale, Tensor B_scale, Tensor workspace_buffer, "
+    "int cublas_handle) -> ()");
   m.impl("bmm_fp8", torch::kCUDA, &bmm_fp8);
   ```