tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-20 17:49:18 +00:00
Code Issues Packages Projects Releases Wiki Activity

rpc : update README for cache usage (#12620)

Browse Source
This commit is contained in:
Radoslav Gerganov
2025-03-28 09:44:13 +02:00
committed by GitHub
parent 13731766db
commit ef03229ff4
1 changed files with 11 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
examples/rpc/README.md
View File

@ -72,3 +72,14 @@ $ bin/llama-cli -m ../models/tinyllama-1b/ggml-model-f16.gguf -p "Hello, my name
This way you can offload model layers to both local and remote devices.
### Local cache
The RPC server can use a local cache to store large tensors and avoid transferring them over the network.
This can speed up model loading significantly, especially when using large models.
To enable the cache, use the `-c` option:
```bash
$ bin/rpc-server -c
```
By default, the cache is stored in the `$HOME/.cache/llama.cpp/rpc` directory and can be controlled via the `LLAMA_CACHE` environment variable.