zhangyiss/mlx-examples
1
0
Fork 0
mirror of https://github.com/ml-explore/mlx-examples.git synced 2025-09-18 19:10:08 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

reorg + fixes to caching, unify prompt caching across types and use cases for e.g. caching during a chat

Browse Source
This commit is contained in:
Awni Hannun
2024-10-05 14:49:39 -07:00
parent ed060a7c5c
commit 782f5a71b7
40 changed files with 824 additions and 691 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
llms/README.md
View File

@@ -155,14 +155,14 @@ different queries. To cache a prompt use `mlx_lm.cache_prompt`. For example:
cat prompt.txt | mlx_lm.cache_prompt \
--model mistralai/Mistral-7B-Instruct-v0.3 \
--prompt - \
--kv-cache-file mistral_prompt.safetensors
--prompt-cache-file mistral_prompt.safetensors
```
Then use the cached prompt with `mlx_lm.generate`:
```
mlx_lm.generate \
--kv-cache-file mistral_prompt.safetensors \
--prompt-cache-file mistral_prompt.safetensors \
--prompt "\nSummarize the above text."
```