mirror of
https://github.com/ollama/ollama.git
synced 2026-10-21 11:01:33 +00:00
c0f8da35b2
* 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 |
||
|---|---|---|
| .. | ||
| architectures | ||
| audio | ||
| cohere2_moe | ||
| dflash | ||
| gemma4 | ||
| glimmer | ||
| glm4_moe_lite | ||
| laguna | ||
| llama | ||
| nemotron_h | ||
| qwen3 | ||
| qwen3_5 | ||
| qwen3_5_moe | ||
| qwen4_exp | ||
| embedding.go | ||
| embedding_test.go | ||
| globalscale.go | ||
| globalscale_test.go | ||
| linear.go | ||
| media.go | ||
| model.go | ||
| quant.go | ||
| root.go | ||