JB Huang is building an LLM training & inference course playlist covering RL, spec decoding, serving
jbhuang0604 · x · 2026-10-31
JB Huang is building a playlist/course for LLM training and inference (work in progress), already covering core topics including:
- Distributed training
- Fine-tuning
- RL
- OPD
- Serving
- Speculative decoding
- Basic optimizers
He's publicly asking what else to include to make the curriculum more complete, inviting the community to help shape this systematic learning resource.
More from Research
- CS312 course post explains sharpness and the edge of stability in LLM pretraining — tatsu_hashimoto · 2026-10-31
- AI decodes wolf howls: 500K hours of Yellowstone audio analyzed by models — aza · 2026-10-31
- NBER paper: training your AI replacement can actually raise workers' pay — joshgans · 2026-10-31
- Trata's Hedge-Bench: no model tops 50% on real-world financial forecasting — ycombinator · 2026-10-31
- Anthropic's internal Claude model claims 2^o(n) 3-SAT algorithm, purportedly refuting the ETH — ctjlewis · 2026-10-31
- CMU paper unifies pretraining, SFT and RL into one likelihood-based training algorithm — rohanpaul_ai · 2026-10-31