"torchvision/vscode:/vscode.git/clone" did not exist on "b56f17ae1ae8a5d08067c7f7444af21fb3b59ca6"
Commit 117a8d2f authored by Azure's avatar Azure
Browse files

fix compilation

parent 3986e2d2
......@@ -15,7 +15,10 @@
#include <torch/torch.h>
#include <cstdint>
#include <c10/cuda/CUDAGuard.h>
#ifdef KTRANSFORMERS_USE_ROCM
typedef hip_bfloat16 nv_bfloat16;
#endif
__global__ void dequantize_q8_0_fp32_kernel(const int8_t* data, float* output, const int blk_size, const int ele_per_blk, const int num_blocks) {
long long global_idx = blockIdx.x * blockDim.x + threadIdx.x;
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment