v0.34.4-rc0: mlx: speed up Qwen 3.8 prompt processing (#18550)
Mirrored from Ollama releases for archival readability. Support the source by reading on the original site.
- mlx: speed up Qwen 3.8 prompt processing
Use MLX's gated-delta kernel for long scans and fold dense MLP global scales into SwiGLU.
- address comments
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.