[NVIDIA] Support nvfp4 quantization (#12784)
This commit is contained in:
@@ -1,5 +1,7 @@
|
||||
#pragma once
|
||||
|
||||
#include <stdio.h>
|
||||
|
||||
#if defined(__CUDACC__) || defined(_NVHPC_CUDA)
|
||||
#define HOST_DEVICE_INLINE __forceinline__ __host__ __device__
|
||||
#define DEVICE_INLINE __forceinline__ __device__
|
||||
@@ -10,6 +12,16 @@
|
||||
#define HOST_INLINE inline
|
||||
#endif
|
||||
|
||||
#define CUDA_CHECK(cmd) \
|
||||
do { \
|
||||
cudaError_t e = cmd; \
|
||||
if (e != cudaSuccess) { \
|
||||
printf("Failed: Cuda error %s:%d '%s'\n", __FILE__, __LINE__, \
|
||||
cudaGetErrorString(e)); \
|
||||
exit(EXIT_FAILURE); \
|
||||
} \
|
||||
} while (0)
|
||||
|
||||
int64_t get_device_attribute(int64_t attribute, int64_t device_id);
|
||||
|
||||
int64_t get_max_shared_memory_per_block_device_attribute(int64_t device_id);
|
||||
|
||||
Reference in New Issue
Block a user