GitHub
TensorTonic/llm-optimization-handbook
Make LLMs faster, cheaper and smaller: inference fundamentals, quantization, KV cache, speculative decoding, GPU kernels and serving, with hands-on problems.
- Stars
- 98
- Forks
- 4
- Stars gained in 24 hours
- +35
- Forks gained in 24 hours
- +2
Topics: cuda, flash-attention, inference, kv-cache, llm, llm-optimization, machine-learning, quantization, speculative-decoding, triton
Latest data point: Nov 21, 2026 · 98 stars · 4 forks