Mention HTTP server in features in README.md

master
Mikko Juola 3 years ago
parent a8320613a1
commit d85ed7f23e

@ -8,6 +8,8 @@ RLLaMA is a pure Rust implementation of [LLaMA large language model inference.](
* LLaMA-7B, LLaMA-13B, LLaMA-30B, LLaMA-65B all confirmed working
* Hand-optimized AVX2 implementation
* OpenCL support for GPU inference.
* Simple HTTP API support, with the possibility of doing token sampling on
client side
## Performance

Loading…
Cancel
Save