Sequoia: Speculative decoding boosting LLM inference by 8-10x
infini-ai-lab.github.io
Sequoia: Speculative decoding boosting LLM inference by 8-10x
1–1 of 1 posts
1–1 of 1 posts
Sequoia: Speculative decoding boosting LLM inference by 8-10x
infini-ai-lab.github.io