doc/README: mention GOMAXPROCS is passed through to llama.cpp

2023-04-09 11:14:19 +12:00 · 2023-04-09 11:14:19 +12:00 · 082fb7552a
parent 2f4558b68e
commit 082fb7552a
1 changed files with 2 additions and 0 deletions
--- a/README.md
+++ b/README.md
@ -22,6 +22,8 @@ LCH_MODEL_PATH=/srv/llama/ggml-vicuna-13b-4bit-rev1.bin \
 	./llamacpphtmld
 ```

+Use the `GOMAXPROCS` environment variable to control how many threads the llama.cpp engine uses.
+
 ## API usage

 The `generate` endpoint will live stream new tokens into an existing conversation until the LLM stops naturally.