Nicholai/jan
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Changed MMAP to mmap

Browse Source
This commit is contained in:
Ashley 2025-01-14 12:14:46 +07:00
parent 0048fe022f
commit 54aae456c4
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docs/src/pages/docs/local-engines/llama-cpp.mdx
View File

@ -150,7 +150,7 @@ For detailed hardware compatibility, please visit our guide for [Mac](/docs/desk
| **Flash Attention** | - Optimizes attention computation<br></br>- Reduces memory usage<br></br>- Recommended for most cases | Enabled |
| **Caching** | - Enable to store recent prompts and responses<br></br>- Improves response time for repeated prompts | Enabled |
| **KV Cache Type** | - KV cache implementation type; controls memory usage and precision trade-off<br></br>- Options:<br></br>• f16 (most stable)<br></br>• q8_0 (balanced)<br></br>• q4_0 (lowest memory) | f16 |
| **MMAP** | - Enables memory-mapped model loading<br></br>- Reduces memory usage<br></br>- Recommended for large models | Enabled |
| **mmap** | - Enables memory-mapped model loading<br></br>- Reduces memory usage<br></br>- Recommended for large models | Enabled |
## Best Practices