MIT 6.5940 EfficientML: Free Lectures on Quantization and Efficient LLM Deployment
techNmak · x · 2026-10-17
Entry 5 in an LLM inference learning list: MIT 6.5940 TinyML and Efficient Deep Learning Computing. The author recommends the 2024 lectures on quantization and efficient LLM deployment — the compression techniques behind smaller, cheaper models. The course covers pruning, quantization, NAS, distributed training, data/model parallelism, and includes hands-on deployment of Llama2-7B on a laptop; all videos are free online.
More from Infra
- MiniCPM-V 4.7 runs locally at 100 tok/s using only ~3 GB of memory — NielsRogge · 2026-10-17
- Power-management chips: the invisible layer deciding AI data center energy efficiency — Olivier__OG · 2026-10-17
- MiniCPM-V 4.7 runs a 35B multimodal model in 3GB of memory, fully on-device — alifcoder · 2026-10-17
- Full FP8 n-gram table visibly improves local Qwen3.8-Flash-Next at zero speed cost — sillynoobhorse · 2026-10-17
- Local Nemotron 3.5 on one A100 hits 169 tok/s, processes 100 clinical notes for 2.4 cents — MaziyarPanahi · 2026-10-17
- NVIDIA's open-source AIPerf benchmarking tool and Triton GPU tutorials for inference measurement — techNmak · 2026-10-17