root
/
ollama
mirror of https://github.com/ollama/ollama.git
1
0
Fork 0
Code Issues Actions Packages Projects Releases Wiki Activity
ollama/runner
History
Jesse Gross 8111c35be8 llm: New memory management 
This changes the memory allocation strategy from upfront estimation to
tracking actual allocations done by the engine and reacting to that. The
goal is avoid issues caused by both under-estimation (crashing) and
over-estimation (low performance due to under-utilized GPUs).

It is currently opt-in and can be enabled for models running on the
Ollama engine by setting OLLAMA_NEW_ESTIMATES=1. Behavior in other
cases is unchanged and will continue to use the existing estimates.
 		2025-08-20 16:56:54 +02:00
..
common chore: fix some inconsistent function name in comment 2025-08-20 16:41:49 +02:00
llamarunner llm: New memory management 2025-08-20 16:56:54 +02:00
ollamarunner llm: New memory management 2025-08-20 16:56:54 +02:00
README.md Runner for Ollama engine 2025-02-13 17:09:26 -08:00
runner.go Runner for Ollama engine 2025-02-13 17:09:26 -08:00

README.md

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