Hitesh Yadav bc9459df40 refactor(inference): modularize model architecture for improved maintainability ... 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		2025-01-05 16:28:10 +05:30
..
configs	Release DeepSeek-V3	2024-12-26 19:01:57 +08:00
models	refactor(inference): modularize model architecture for improved maintainability	2025-01-05 16:28:10 +05:30
convert.py	require model-parallel in convert.py	2024-12-31 18:05:55 +08:00
fp8_cast_bf16.py	handle missing scale_inv_name (#2)	2024-12-27 09:34:38 +08:00
generate.py	Release DeepSeek-V3	2024-12-26 19:01:57 +08:00
kernel.py	Release DeepSeek-V3	2024-12-26 19:01:57 +08:00
model.py	torch rmsnorm	2025-01-05 14:33:48 +08:00
requirements.txt	Release DeepSeek-V3	2024-12-26 19:01:57 +08:00