Uv and Ray: Pain-Free Python Dependencies in Clusters(anyscale.com)29 points by robertnishihara 1 year ago | 8 comments
ThirdAI Uses Ray for Parallel Training of Billion-Parameter NN on Commodity CPUs(anyscale.com)52 points by thirdailab 3 years ago | 11 comments
Llama 2 is about as factually accurate as GPT-4 for summaries and is 30X cheaper(anyscale.com)71 points by pallas_athena 3 years ago | 19 comments
Continuous batching to increase LLM inference throughput and reduce p50 latency(anyscale.com)98 points by michellezzz 3 years ago | 19 comments
Fine-Tuning Llama-2: A Comprehensive Case Study for Tailoring Custom Models(anyscale.com)268 points by robertnishihara 3 years ago | 54 comments