Scaling Up Efficient Small Language Models Serving and Deployment for Semantic Job Search
This work addresses the deployment challenges of language models for industry applications like job search, offering incremental improvements in efficiency.
The paper tackles the high cost and latency of deploying large language models for semantic search by developing a small language model with compression techniques, achieving a 40% model size reduction, 10x context compression, and 10x throughput increase in a real-world deployment at LinkedIn.
Large Language Models (LLMs) have demonstrated impressive quality when applied to predictive tasks such as relevance ranking and semantic search. However, deployment of such LLMs remains prohibitively expensive for industry applications with strict latency and throughput requirements. In this work, we present lessons and efficiency insights from developing a purely text-based decoder-only Small Language Model (SLM) for a semantic search application at LinkedIn. Particularly, we discuss model compression techniques such as pruning that allow us to reduce the model size by up to $40\%$ while maintaining the accuracy. Additionally, we present context compression techniques that allow us to reduce the input context length by up to $10$x with minimal loss of accuracy. Finally, we present practical lessons from optimizing the serving infrastructure for deploying such a system on GPUs at scale, serving millions of requests per second. Taken together, this allows us to increase our system's throughput by $10$x in a real-world deployment, while meeting our quality bar.