|
…
|
|
attention.h
|
Add architecture-variant waves 1+2: train...
|
5 days ago |
|
config.h
|
Add wave 3: DeepSeek-V3-style MoE routing, all config-selected
|
5 days ago |
|
embedding.h
|
Forge: LLM training from scratch in C++20 + Metal on Apple Silicon
|
10 days ago |
|
linear.cpp
|
Add QAT, MoE, and architecture-variant knobs — all config-selected
|
5 days ago |
|
linear.h
|
Add QAT, MoE, and architecture-variant knobs — all config-selected
|
5 days ago |
|
mlp.h
|
Add wave 3: DeepSeek-V3-style MoE routing, all config-selected
|
5 days ago |
|
module.h
|
Forge: LLM training from scratch in C++20 + Metal on Apple Silicon
|
10 days ago |
|
transformer.h
|
Add wave 3: DeepSeek-V3-style MoE routing, all config-selected
|
5 days ago |