[Kernel] Add JIT rotary_embedding_kernel (#17934)
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> Co-authored-by: Xiaoyu Zhang <35585791+BBuf@users.noreply.github.com> Co-authored-by: root <root@zhikuan-A10x2.ea134>
This commit is contained in:
@@ -28,6 +28,15 @@ using fp8x2_e5m2_t = __nv_fp8x2_e5m2;
|
||||
using fp32x4_t = float4;
|
||||
#endif
|
||||
|
||||
/*
|
||||
* LDG Support
|
||||
*/
|
||||
#ifndef USE_ROCM
|
||||
#define SGLANG_LDG(arg) __ldg(arg)
|
||||
#else
|
||||
#define SGLANG_LDG(arg) *(arg)
|
||||
#endif
|
||||
|
||||
namespace device {
|
||||
|
||||
#define SGL_DEVICE __forceinline__ __device__
|
||||
|
||||
Reference in New Issue
Block a user