|
configs
|
chore: commit pending workspace changes
|
yesterday |
|
models
|
Add wave 3: DeepSeek-V3-style MoE routing, all config-selected
|
5 days ago |
|
paper
|
Forge: LLM training from scratch in C++20 + Metal on Apple Silicon
|
10 days ago |
|
src
|
Add elapsed_s column to log.csv for structured metrics consumers
|
5 days ago |
|
tests
|
Add wave 3: DeepSeek-V3-style MoE routing, all config-selected
|
5 days ago |
|
third_party
|
Forge: LLM training from scratch in C++20 + Metal on Apple Silicon
|
10 days ago |
|
tools
|
Add HF streaming data pipeline and three research reports
|
5 days ago |
|
.gitignore
|
Forge: LLM training from scratch in C++20 + Metal on Apple Silicon
|
10 days ago |
|
ARCHITECTURES.md
|
Add wave 3: DeepSeek-V3-style MoE routing, all config-selected
|
5 days ago |
|
CLAUDE.md
|
Forge: LLM training from scratch in C++20 + Metal on Apple Silicon
|
10 days ago |
|
CMakeLists.txt
|
Add .forge — Apple-native, git-style weight format with zero-copy...
|
5 days ago |
|
INFERENCE_RESEARCH.md
|
Add HF streaming data pipeline and three research reports
|
5 days ago |
|
LICENSE
|
Forge: LLM training from scratch in C++20 + Metal on Apple Silicon
|
10 days ago |
|
README.md
|
Add HF streaming data pipeline and three research reports
|
5 days ago |
|
RESEARCH.md
|
Forge: LLM training from scratch in C++20 + Metal on Apple Silicon
|
10 days ago |
|
SMALL_MODELS_RESEARCH.md
|
Add HF streaming data pipeline and three research reports
|
5 days ago |