MLX v0.32.0 发布：多项修复与平台支持增强

AI 摘要

MLX 发布了 v0.32.0 版本，包含多项修复和改进，如 CUDA 内核修复、新增行列式函数、支持 Windows JIT 编译、默认启用 iOS Metal 后端等。这些更新提升了 MLX 在多种平台上的性能和稳定性。

正文节选

## What's Changed * Generate qmm implementaions with cmake by @zcbenz in https://github.com/ml-explore/mlx/pull/3424 * Enable swap for all CI building CUDA by @zcbenz in https://github.com/ml-explore/mlx/pull/3437 * Bump minor by @angeloskath in https://github.com/ml-explore/mlx/pull/3438 * [CUDA] Fix qmm_naive K-tail dispatch for FP quantized kernels by @Lyxot in https://github.com/ml-explore/mlx/pull/3445 * Keep gguflib input-validation asserts active in release builds by @qflen in https:

发布时间：2026-07-08 06:29

抓取时间：2026-08-02 00:31

来源机构：Apple