Chili Palmer 5bf170cedb removed kv quantization due to incompatibility with gemma3

2026-03-17 09:20:35 +01:00

mlx_server

removed kv quantization due to incompatibility with gemma3

2026-03-17 09:20:35 +01:00

.gitignore

initial commit

2026-03-17 09:14:27 +01:00

CLAUDE.md

initial commit

2026-03-17 09:14:27 +01:00

pyproject.toml

initial commit

2026-03-17 09:14:27 +01:00

run.sh

initial commit

2026-03-17 09:14:27 +01:00

test_server.py

initial commit

2026-03-17 09:14:27 +01:00

Description

a simple MLX based server for small models to run locally

MIT 3.3 MiB

Languages

Swift 99.6%

Shell 0.4%