TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients. Published in Nature.
- large-language-models
- prompt-optimization
- compound-systems
- textual-gradients
98,836 visible repositories in the index
25–48 of 57 · Most stars
TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients. Published in Nature.
Switchyard lets LLM applications route traffic across models and providers while preserving native OpenAI and Anthropic API compatibility - enabling flexible model selection, benchmarking, and cost/performance optimization.
Find the ghost tokens. Fix them. Survive compaction. Avoid context quality decay.
Reference implementation for DPO (Direct Preference Optimization)
vLLM’s reference system for K8S-native cluster-wide deployment with community-driven performance optimization
The NVIDIA NeMo Agent toolkit is an open-source library for efficiently connecting and optimizing teams of AI agents.
Olive: Simplify ML Model Finetuning, Conversion, Quantization, and Optimization for CPUs, GPUs and NPUs.
An optimized deep prompt tuning strategy comparable to fine-tuning across scales and tasks
Run LLMs on AMD Ryzen™ AI NPUs in minutes; purpose-built and deeply optimized for the AMD NPUs.
14-stage Fusion Pipeline for LLM token compression — reversible compression, AST-aware code analysis, intelligent content routing. Zero LLM inference cost. MIT licensed.
An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs
Optimized Agentic and LLM Bulk Processing Over Your Data
Building blocks for rapid development of GenAI applications
A high-performance inference engine for LLM, VLM and DiT models, optimized for diverse AI accelerators. It is hosted in OpenAtom Foundation.
Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B
A toolkit to create optimal Production-readyRetrieval Augmented Generation(RAG) setup for your data
Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success
Non-destructive compression gateway for AI coding agents. Cuts token bills 25% on turn 1 to past 85% in long or saturated sessions, and fits ~3× more turns in the same context window. Powered by our open-source code-native 4B model. Drop-in for Claude Code, Cursor, Codex, OpenHands, and any BASE_URL agent.
Scalable and memory-optimized training of diffusion models
A framework for comprehensive diagnosis and optimization of agents using simulated, realistic synthetic interactions
Local inference engine optimized for NVIDIA Blackwell
Run MoE models bigger than your RAM. Frontier-size MoE on a phone, laptop, edge. Lossless, on stock llama.cpp. An adaptive streaming optimizer. Any hardware, any OS, any model, any quantization, behind a local OpenAI-compatible server.
Blazing fast Apple Silicon inference engine optimized for Qwen & Nemotron. OpenAI + Anthropic API compatible. Built by folks from nace.ai
Scikit-learn for Recursive Self-improvement (RSI). A modular framework for recursive harness evolution.