1 repository
Sending multiple concurrent requests to increase the rate of text generation or training throughput.
Distinct from Training Throughput Optimization: Distinct from Training Throughput Optimization: focuses on async request concurrency for inference and training, not batch size selection.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Async Request Throughput Optimizers. Refine with filters or upvote what's useful.
Tinker Cookbook is an open-source framework for fine-tuning large language models, supporting supervised learning, reinforcement learning, and parameter-efficient techniques like LoRA adapters. It provides a complete pipeline for aligning models with human preferences through multi-stage RLHF workflows, from supervised fine-tuning through preference optimization to reinforcement learning. The framework distinguishes itself through recipe-based training orchestration, where fine-tuning workflows are defined as composable recipe files that chain data loading, model configuration, and training l
Optimizes throughput by sending multiple concurrent generation requests asynchronously.