rltakashige 3f0df404a5 Reduce memory consumption by adding Flash Attention to Qwen3.5 and Gemma 4, and fix RotatingKVCache prefix cache memory leak (#1886) ...

## Motivation

Part 1 of many memory improvements.

## Changes
As written in the title

## Test Plan

### Manual Testing
Gemma 4 26B cache reduced from 54GB -> 10GB per 100k tokens, Qwen3.5 35B
A3B cache reduced from 21GB every 100000 tokens to 7GB.

2026-04-13 18:32:17 +01:00

..

apple-sdk/metadata

nix: override apple-sdk to 26.2 and enable MLX_BUILD_CPU (#1443)

2026-02-10 19:53:53 +00:00

apple-sdk-overlay.nix

nix: override apple-sdk to 26.2 and enable MLX_BUILD_CPU (#1443)

2026-02-10 19:53:53 +00:00

darwin-build-fixes.patch

Fix BatchGenerator in line with upstream refactor (and prevent Qwen3.5 memory leak) (#1835)

2026-04-07 11:50:12 +00:00

metal-toolchain.nix

mlx: build with Nix (#1285)

2026-01-29 14:07:00 +00:00

mlx.nix

Reduce memory consumption by adding Flash Attention to Qwen3.5 and Gemma 4, and fix RotatingKVCache prefix cache memory leak (#1886)

2026-04-13 18:32:17 +01:00