SGLang is a new system that speeds up structured LLM programs by up to 6.4x using RadixAttention for KV cache reuse and compressed finite state machines for output decoding.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 1years
2023 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
SGLang: Efficient Execution of Structured Language Model Programs
SGLang is a new system that speeds up structured LLM programs by up to 6.4x using RadixAttention for KV cache reuse and compressed finite state machines for output decoding.