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

Fix trailing whitespace

Browse source
This commit is contained in:
JohannesGaessler 2023-06-18 15:47:02 +02:00
parent d036161b14
commit a794320fc8
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
README.md
View file

@ -338,7 +338,7 @@ Building the program with BLAS support may lead to some performance improvements
```
The environment variable [`CUDA_VISIBLE_DEVICES`](https://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#env-vars) can be used to specify which GPU(s) will be used. The following compilation options are also available to tweak performance:
| Option | Legal values | Default | Description |
|-------------------------|------------------------|---------|-------------|
| LLAMA_CUDA_DMMV_X | Positive integer >= 32 | 32 | Number of values in x direction processed by the CUDA dequantization + matrix vector multiplication kernel per iteration. Increasing this value can improve performance on fast GPUs. Power of 2 heavily recommended. Does not affect k-quants. |