mlx-examples/llms/decilm/__init__.py

"""DeciLM support for MLX."""

from .decilm import DeciLMArgs, Model

__all__ = ["DeciLMArgs", "Model"]
Add DeciLM/Nemotron-NAS architecture support for MLX This commit introduces native MLX support for DeciLM models, including NVIDIA's Nemotron series that use Neural Architecture Search (NAS) optimizations. Key features: - Support for dummy layers (no-op attention/FFN components) - FFN fusion for improved efficiency - Variable Grouped Query Attention (VGQA) with different KV heads per layer - Block configuration handling for NAS architectures - Full conversion pipeline from HuggingFace to MLX format - Comprehensive test suite Tested with: - nvidia/Llama-3_1-Nemotron-Ultra-253B-v1 (Q5: 3.86 tokens/sec on M3 Ultra) - Memory usage: ~175GB peak for 253B model This enables running massive NAS-optimized models on Apple Silicon that were previously incompatible with MLX due to their unique architecture. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com> 2025-07-02 11:59:09 +08:00			`"""DeciLM support for MLX."""`

			`from .decilm import DeciLMArgs, Model`

			`__all__ = ["DeciLMArgs", "Model"]`