diff options
| author | Johannes Gäßler <johannesg@5d6.de> | 2023-05-13 15:38:36 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-05-13 16:38:36 +0300 |
| commit | 905d87b70aa189623d500a28602d7a3a755a4769 (patch) | |
| tree | 11f0d435ecb7555734b14b7a8994e88772bf8190 /ggml-cuda.h | |
| parent | f954edda935a70a14cf0cc45ecc7fe7d60cf3e4b (diff) | |
ggml : GPU-accelerated token generation (#1412)
* CUDA kernel for q4_0 dequant. + mat. vec. mult.
* Added q4_1 via template
* Added missing __syncthreads();
* --gpu_layers -> --gpu-layers
* Shorter dequantize_mul_mat_vec line
* q5_0 dequantize_mul_mat kernel
* More readable dequantize_mul_mat_vec logic
* dequantize_mul_mat_vec kernels for q5_1, q8_0, f16
* llama : offload "output" tensor to GPU too + coding style fixes
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Diffstat (limited to 'ggml-cuda.h')
| -rw-r--r-- | ggml-cuda.h | 2 |
1 files changed, 2 insertions, 0 deletions
diff --git a/ggml-cuda.h b/ggml-cuda.h index f7d6a8bc..4e2c2428 100644 --- a/ggml-cuda.h +++ b/ggml-cuda.h @@ -14,6 +14,8 @@ void ggml_cuda_mul_mat(const struct ggml_tensor * src0, const struct ggml_tens void * ggml_cuda_host_malloc(size_t size); void ggml_cuda_host_free(void * ptr); +void ggml_cuda_transform_tensor(struct ggml_tensor * tensor); + #ifdef __cplusplus } #endif |