Stories by robertnishihara

RAG at Scale: 10x Cheaper Embedding Computations with Anyscale and Pinecone

Comparing LLM Performance: Introducing the Open Source Leaderboard for LLM APIs

LLMPerf Leaderboard

LLM summarization: A case study of human, Llama-2, & GPT-4 summarization quality

Reproducible Performance Metrics for LLM Inference

Building Rag-Based LLM Applications for Production

Anyscale Endpoints: LLM inference and fine-tuning

Anyscale Private Endpoints and Anyscale Endpoints Fine-Tuning

Loading Llama-2 70B 20x faster with Anyscale Endpoints

A Comprehensive Guide for Building Rag-Based LLM Applications

Llama 2 is about as factually accurate as GPT-4 for summaries and is 30X cheaper

Nearly all LLMs will be multi-modal

ByteDance Scales Offline Inference with Multi-Modal LLMs to 200 TB Data

Fine-Tuning Llama-2: A Comprehensive Case Study for Tailoring Custom Models

Distributed Machine Learning at Instacart

Training One Million Machine Learning Models in Record Time with Ray

An informal introduction to reinforcement learning

Introducing Anyscale: The Future Is Distributed

Why Third Generation ML Platforms Are More Performant

Analyzing memory management and performance in Dask-on-Ray

1
2