all AI news
Prompt Lookup Decoding
Jan. 23, 2024, 2:14 a.m. |
Simon Willison's Weblog simonwillison.net
Really neat LLM optimization trick by Apoorv Saxena, who observed that it's common for sequences of tokens in LLM input to be reflected by the output - snippets included in a summarization, for example.
Apoorv's code performs a simple search for such prefixes and uses them to populate a set of suggested candidate IDs during LLM token generation.
The result appears to provide around a 2.4x speed-up in generating outputs!
Via @abacaj
ai code decoding example generativeai llm llms optimization prompt search set simple summarization them tokens trick
More from simonwillison.net / Simon Willison's Weblog
Jobs in AI, ML, Big Data
Software Engineer for AI Training Data (School Specific)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Python)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Tier 2)
@ G2i Inc | Remote
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US