Jesse Gross 21aa666a1e ml: Enable support for flash attention
The GGML flash attention kernel has specific requirements for
padding and permutation. This adds support to the KV cache
for conforming to these requirements so that flash attention
can be enabled.

Flash attention can be used in the same situations as the llama
engine and is enabled by the user in the same way.
2025-03-01 20:53:23 -08:00
..
2025-02-13 17:09:26 -08:00
2025-02-28 22:27:28 +00:00
2025-02-13 17:09:26 -08:00
2025-02-13 17:09:26 -08:00

runner

Note: this is a work in progress

A minimial runner for loading a model and running inference via a http web server.

./runner -model <model binary>

Completion

curl -X POST -H "Content-Type: application/json" -d '{"prompt": "hi"}' http://localhost:8080/completion

Embeddings

curl -X POST -H "Content-Type: application/json" -d '{"prompt": "turn me into an embedding"}' http://localhost:8080/embedding