vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

remove extra stuff

Browse source
This commit is contained in:
Henri Vasserman 2023-04-28 17:47:55 +03:00
parent d9bc43c555
commit 87864d99a9
No known key found for this signature in database
GPG key ID: 2995FC0F58B1A986
2 changed files with 0 additions and 14 deletions
Download patch file Download diff file Expand all files Collapse all files

10
ggml-cuda.cu
View file

@ -340,16 +340,6 @@ void ggml_init_cublas(void) {
} }
} }
void * ggml_cuda_host_malloc(size_t size) {
void * ptr;
CUDA_CHECK(cudaMallocHost((void **) &ptr, size));
return ptr;
}
void ggml_cuda_host_free(void * ptr) {
CUDA_CHECK(cudaFreeHost(ptr));
}
cudaError_t ggml_cuda_cpy_tensor2D(void * dst, const struct ggml_tensor * src, uint64_t i3, uint64_t i2, cudaStream_t stream) { cudaError_t ggml_cuda_cpy_tensor2D(void * dst, const struct ggml_tensor * src, uint64_t i3, uint64_t i2, cudaStream_t stream) {
const uint64_t ne0 = src->ne[0]; const uint64_t ne0 = src->ne[0];
const uint64_t ne1 = src->ne[1]; const uint64_t ne1 = src->ne[1];

4
ggml-cuda.h
View file

@ -40,12 +40,8 @@ void dequantize_row_q5_0_cuda(const void * vx, float * y, int k, cudaStream_t st
void dequantize_row_q5_1_cuda(const void * vx, float * y, int k, cudaStream_t stream); void dequantize_row_q5_1_cuda(const void * vx, float * y, int k, cudaStream_t stream);
void dequantize_row_q8_0_cuda(const void * vx, float * y, int k, cudaStream_t stream); void dequantize_row_q8_0_cuda(const void * vx, float * y, int k, cudaStream_t stream);
void ggml_cuda_convert_fp16_to_fp32(const ggml_fp16_t * x, float * y, int n, cudaStream_t stream);
cudaError_t ggml_cuda_cpy_tensor2D(void * dst, const struct ggml_tensor * src, uint64_t i3, uint64_t i2, cudaStream_t stream); cudaError_t ggml_cuda_cpy_tensor2D(void * dst, const struct ggml_tensor * src, uint64_t i3, uint64_t i2, cudaStream_t stream);
typedef void (*dequantize_row_q_cuda_t)(const void * x, float * y, int k, cudaStream_t stream);
dequantize_row_q_cuda_t ggml_get_dequantize_row_q_cuda(enum ggml_type type);
#ifdef __cplusplus #ifdef __cplusplus
} }
#endif #endif