Sign in Subscribe

generation latency

GPT-4 is Getting Faster 🐇

GPT-4 is Getting Faster 🐇

Over the past few months, we've been keenly observing latencies for both GPT 3.5 & 4. The emerging patterns have been intriguing. The standout observation? GPT-4 is catching up in speed, closing the latency gap with GPT 3.5. Our findings reveal a consistent decline in GPT-4

Skeleton-of-Thought: Large Language Models Can Do Parallel Decoding - Summary

Skeleton-of-Thought: Large Language Models Can Do Parallel Decoding - Summary

This paper introduces the Skeleton-of-Thought (SoT) method to decrease the generation latency of large language models (LLMs). SoT guides LLMs to first generate the skeleton of the answer and then conducts parallel API calls or batched decoding to complete the contents of each skeleton point. The m