ExternalVendorCode/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2025-06-12 20:18:08 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

move BLAS to a separate backend (cont) (llama/6210)

Browse Source 
ggml-ci
This commit is contained in:
slaren
2024-06-16 13:57:37 +03:00
committed by Georgi Gerganov
parent 922971041b
commit de29b193f6
5 changed files with 773 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/common.h
View File

@ -21,7 +21,7 @@ struct gpt_params {
int32_t n_threads = std::min(4, (int32_t) std::thread::hardware_concurrency());
int32_t n_predict = 200; // new tokens to predict
int32_t n_parallel = 1; // number of parallel streams
int32_t n_batch = 8; // batch size for prompt processing
int32_t n_batch = 32; // batch size for prompt processing
int32_t n_ctx = 2048; // context size (this is the KV cache max size)
int32_t n_gpu_layers = 0; // number of layers to offlload to the GPU