github-featured / ollama--ollama

发布

0 发布 616 Git 标签

RSS 订阅源
  • v0.17.8-rc2 539741199e
    比较

    mlx: perf improvements (#14768)

    frostbyte_neo 发布于 2026-03-12 19:01:28 +00:00

    • mlx: perf improvements

    Fix nn.go to call mlx_fast_layer_norm instead of manually implementing (mean,
    subtract, variance, rsqrt, multiply, add — 6 ops)

    Fix llama.go, gemma3.go to remove RepeatKV to tile K/V tensors to match the Q
    head count, since scaled_dot_product_attention natively handles GQA (it just
    requires n_q_heads % n_kv_heads == 0)

    • review comments
    下载附件