mmarch/text-generation-webui
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Add in-memory cache support for llama.cpp (#1936)

Browse source
This commit is contained in:
Andrei 2023-05-15 19:19:55 -04:00 • committed by GitHub
parent 0227e738ed
commit e657dd342d
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
3 changed files with 33 additions and 16 deletions
Download patch file Download diff file Expand all files Collapse all files

1
README.md
View file

@ -230,6 +230,7 @@ Optionally, you can use the following command-line flags:
| `--n_batch` | Maximum number of prompt tokens to batch together when calling llama_eval. |
| `--no-mmap` | Prevent mmap from being used. |
| `--mlock` | Force the system to keep the model in RAM. |
| `--cache-capacity CACHE_CAPACITY` | Maximum cache capacity. Examples: 2000MiB, 2GiB. When provided without units, bytes will be assumed. |
| `--n-gpu-layers N_GPU_LAYERS` | Number of layers to offload to the GPU. Only works if llama-cpp-python was compiled with BLAS. Set this to 1000000000 to offload all layers to the GPU. |
#### GPTQ