v0.34.4-rc0: mlx: speed up Qwen 3.8 prompt processing (#18550)

ollama/ollama Releases Developers & Open Source 09/23/2026, 08:53 Score 7/10

Summary

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

AILLMOpen Source

Lotu Radar provides attributed news summaries and links to the original publisher. Full reporting and copyright remain with the source.