Directories
¶
| Path | Synopsis |
|---|---|
|
Package agent provides agent loop orchestration and tool approval.
|
Package agent provides agent loop orchestration and tool approval. |
|
client
Package client provides client-side model creation for safetensors-based models.
|
Package client provides client-side model creation for safetensors-based models. |
|
Package imagegen provides experimental image generation capabilities for Ollama.
|
Package imagegen provides experimental image generation capabilities for Ollama. |
|
cache
Package cache provides caching mechanisms for diffusion model inference.
|
Package cache provides caching mechanisms for diffusion model inference. |
|
cmd/engine
command
|
|
|
mlx
Package mlx provides Go bindings for the MLX-C library with dynamic loading support.
|
Package mlx provides Go bindings for the MLX-C library with dynamic loading support. |
|
models/flux2
Package flux2 implements the FLUX.2 Klein diffusion transformer model.
|
Package flux2 implements the FLUX.2 Klein diffusion transformer model. |
|
models/qwen3
Package qwen3 provides a shared Qwen3 text encoder used by multiple image generation models.
|
Package qwen3 provides a shared Qwen3 text encoder used by multiple image generation models. |
|
models/zimage
Package zimage implements the Z-Image diffusion transformer model.
|
Package zimage implements the Z-Image diffusion transformer model. |
|
nn
Package nn provides neural network layer types.
|
Package nn provides neural network layer types. |
|
vae
Package vae provides shared utilities for VAE (Variational Autoencoder) operations.
|
Package vae provides shared utilities for VAE (Variational Autoencoder) operations. |
|
internal
|
|
|
mlx/generator
command
|
|
|
models
|
|
|
gemma3
Package gemma3 provides the Gemma 3 text model implementation for MLX.
|
Package gemma3 provides the Gemma 3 text model implementation for MLX. |
|
gemma4
Package gemma4 provides the Gemma 4 text model implementation for MLX.
|
Package gemma4 provides the Gemma 4 text model implementation for MLX. |
|
glm4_moe_lite
Package glm4_moe_lite provides the GLM4-MoE-Lite implementation for MLX.
|
Package glm4_moe_lite provides the GLM4-MoE-Lite implementation for MLX. |
|
laguna
Package laguna provides the Poolside Laguna text model implementation for MLX.
|
Package laguna provides the Poolside Laguna text model implementation for MLX. |
|
llama
Package llama provides a Llama-style decoder-only transformer for MLX.
|
Package llama provides a Llama-style decoder-only transformer for MLX. |
|
qwen3
Package qwen3 provides the Qwen3 text model implementation for MLX.
|
Package qwen3 provides the Qwen3 text model implementation for MLX. |
|
qwen3_5
Package qwen3_5 provides the Qwen 3.5 text and MoE implementation for MLX.
|
Package qwen3_5 provides the Qwen 3.5 text and MoE implementation for MLX. |
|
qwen3_5_moe
Package qwen3_5_moe registers Qwen 3.5 MoE architecture aliases.
|
Package qwen3_5_moe registers Qwen 3.5 MoE architecture aliases. |
|
Package tools provides built-in tool implementations for the agent loop.
|
Package tools provides built-in tool implementations for the agent loop. |
|
Package transfer provides minimal, fast blob transfer for tensor-based models.
|
Package transfer provides minimal, fast blob transfer for tensor-based models. |
Click to show internal directories.
Click to hide internal directories.