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.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.h')
-rw-r--r-- | ggml.h | 8 |
1 files changed, 7 insertions, 1 deletions
@@ -243,6 +243,11 @@ extern "C" { GGML_TYPE_COUNT, }; + enum ggml_backend { + GGML_BACKEND_CPU = 0, + GGML_BACKEND_CUDA = 1, + }; + // model file types enum ggml_ftype { GGML_FTYPE_UNKNOWN = -1, @@ -333,6 +338,7 @@ extern "C" { // n-dimensional tensor struct ggml_tensor { enum ggml_type type; + enum ggml_backend backend; int n_dims; int64_t ne[GGML_MAX_DIMS]; // number of elements @@ -363,7 +369,7 @@ extern "C" { char name[32]; - char padding[8]; // TODO: remove and add padding to name? + char padding[9]; // TODO: remove and add padding to name? }; // computation graph |