mirror of
https://github.com/deepseek-ai/DeepSeek-V3.git
synced 2025-04-20 10:38:57 -04:00
bc9459df40
BREAKING CHANGE: Restructured model.py into dedicated modules under inference/models/ Key Changes: - Split monolithic model.py into focused, single-responsibility modules: - config.py: Model configuration and hyperparameters - attention.py: Multi-head Latent Attention (MLA) implementation - moe.py: Mixture of Experts components (Gate, Expert, MoE) - linear.py: Linear layer variants with parallel processing support - __init__.py: Clean public API exports Benefits: - Improved code organization and maintainability - Better separation of concerns - Enhanced testability of individual components - Clearer dependency management - Simplified future modifications and extensions Migration: - Update imports to use new module structure - No functional changes to existing implementations - Backwards compatible with current model weights
15 lines
306 B
Python
15 lines
306 B
Python
from .config import ModelArgs
|
|
from .attention import MLA
|
|
from .moe import Gate, Expert, MoE
|
|
from .linear import Linear, ColumnParallelLinear, RowParallelLinear
|
|
|
|
__all__ = [
|
|
'ModelArgs',
|
|
'MLA',
|
|
'Gate',
|
|
'Expert',
|
|
'MoE',
|
|
'Linear',
|
|
'ColumnParallelLinear',
|
|
'RowParallelLinear'
|
|
] |