Optimizing your LLM in production

Investing in Performance: Fine-tune small models with LLM insights - a CFM case study

Efficient Request Queueing – Optimizing LLM Performance

Understanding and Coding the KV Cache in LLMs from Scratch

KV caches are one of the most critical techniques for efficient inference in LLMs in production.

How Long Prompts Block Other Requests - Optimizing LLM Performance

Making thousands of open LLMs bloom in the Vertex AI Model Garden

Preference Tuning LLMs with Direct Preference Optimization Methods

Judge Arena: Benchmarking LLMs as Evaluators

Rethinking LLM Evaluation with 3C3H: AraGen Benchmark and Leaderboard

Prefill and Decode for Concurrent Requests - Optimizing LLM Performance

Making LLMs lighter with AutoGPTQ and transformers

Recent Developments in LLM Architectures: KV Sharing, mHC, and Compressed Attention

From Gemma 4 to DeepSeek V4, How New Open-Weight LLMs Are Reducing Long-Context Costs

Optimize and deploy with Optimum-Intel and OpenVINO GenAI