Snider 71fe4bb5ac fix: add Detach/Free calls to reduce Metal GPU memory retention ... Add deterministic memory cleanup across inference paths: - Detach logits after Eval to release graph references - Free intermediate arrays in attention (gemma3, qwen3) - Add cache Detach helper for KV cache cleanup after generation - New detach.cpp/go CGO bindings for mlx_array_detach Reduces 4B model memory from 78GB to ~17GB (vs 2.4GB mlx-lm baseline). Native Metal memory management still trails Python refcounting but is now viable for 1B models. Co-Authored-By: Virgil <virgil@lethean.io>		2026-02-26 05:14:09 +00:00
..
metal_cpp	fix: add Detach/Free calls to reduce Metal GPU memory retention	2026-02-26 05:14:09 +00:00
mlx	chore: vendor MLX C headers for Go module consumers	2026-02-21 19:14:04 +00:00