ExternalVendorCode/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2025-06-17 06:18:08 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

llama : refactor model loader with backend registry (llama/10026)

Browse Source
This commit is contained in:
Diego Devesa
2024-10-30 02:01:23 +01:00
committed by Georgi Gerganov
parent 307712a903
commit 1d48457aa6
14 changed files with 273 additions and 410 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ggml/include/ggml-cuda.h
View File

@ -28,7 +28,7 @@ GGML_API bool ggml_backend_is_cuda(ggml_backend_t backend);
GGML_API ggml_backend_buffer_type_t ggml_backend_cuda_buffer_type(int device);
// split tensor buffer that splits matrices by rows across multiple devices
GGML_API ggml_backend_buffer_type_t ggml_backend_cuda_split_buffer_type(const float * tensor_split);
GGML_API ggml_backend_buffer_type_t ggml_backend_cuda_split_buffer_type(int main_device, const float * tensor_split);
// pinned host buffer for use with the CPU backend for faster copies between CPU and GPU
GGML_API ggml_backend_buffer_type_t ggml_backend_cuda_host_buffer_type(void);