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

readme : add example for main

Browse source
This commit is contained in:
Georgi Gerganov 2023-06-04 18:50:09 +03:00
parent e33002d42e
commit 324e823afd
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
1 changed files with 5 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

6
README.md
View file

@ -255,7 +255,11 @@ Using Metal allows the computation to be executed on the GPU for Apple devices:
``` ```
When built with Metal support, you can enable GPU inference with the `--gpu-layers|-ngl` command-line argument. When built with Metal support, you can enable GPU inference with the `--gpu-layers|-ngl` command-line argument.
Any value larger than 0 will offload the computation to the GPU. Any value larger than 0 will offload the computation to the GPU. For example:
```bash
./main -m ./models/7B/ggml-model-q4_0.bin -n 128 -ngl 1
```
### BLAS Build ### BLAS Build