The Local LLM Index / Quantization & Formats / #134
patchy631/time-to-first-token
by patchy631 · Quantization & Formats · updated 2mo ago
A 10-week, 30-minutes-a-day roadmap for LLM inference serving and optimization. vLLM, SGLang, quantization, speculative decoding, benchmarking.
56
momentum
1,009
stars
113
forks
#134
rank
learning-resourcesllmllm-inferencemlopsroadmapsglangvllm
View on GitHub →