scaling-book 13
- Scaling Book Part 12: 关于 GPU 的一切 (How to Think About GPUs)
- Scaling Book Part 11: 总结与延伸阅读 (Conclusions and Further Reading)
- Scaling Book Part 10: JAX TPU 编程指南 (Programming TPUs in JAX)
- Scaling Book Part 9: 如何分析 TPU 程序性能 (How to Profile TPU Programs)
- Scaling Book Part 8: LLaMA 3 在 TPU 上的服务实战 (Serving LLaMA 3 on TPUs)
- Scaling Book Part 7: 推理 (Inference)
- Scaling Book Part 6: 实战训练 LLaMA (Training LLaMA 3 on TPUs)
- Scaling Book Part 5: 训练 (Training)
- Scaling Book Part 4: 深入理解 Transformers (Transformer Math)
- Scaling Book Part 3: 深入理解分布式矩阵乘法 (Sharded Matmuls)
- Scaling Book Part 2: 关于 TPU 的一切 (All About TPUs)
- Scaling Book Part 1: 关于 Rooflines 的一切 (Intro to Rooflines)
- Scaling Book Part 0: 前言 (Introduction)