Sam 1bdab9fdb1 llm: introduce k/v context quantization (vRAM improvements) (#6279)		5 mesiacov pred
..
README.md	96efd9052f Re-introduce the `llama` package (#5034)	6 mesiacov pred
cache.go	2cd11ae365 runner.go: Add unit tests for context shifting	5 mesiacov pred
cache_test.go	2cd11ae365 runner.go: Add unit tests for context shifting	5 mesiacov pred
image.go	c2e8cbaa14 runner.go: Check for zero length images	5 mesiacov pred
image_test.go	c826e57475 runner.go: Better abstract vision model integration	6 mesiacov pred
requirements.go	96efd9052f Re-introduce the `llama` package (#5034)	6 mesiacov pred
runner.go	1bdab9fdb1 llm: introduce k/v context quantization (vRAM improvements) (#6279)	5 mesiacov pred
stop.go	0077e22d52 runner.go: Handle truncation of tokens for stop sequences	6 mesiacov pred
stop_test.go	0077e22d52 runner.go: Handle truncation of tokens for stop sequences	6 mesiacov pred

`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>

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

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

runner