The LLM Evaluation Framework

A Datacenter Scale Distributed Inference Serving Framework

When AI Fails is a project dedicated to documenting the funny, interesting, and sometimes outright stupid ways in which AI can fail.

[MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

LLM agents built for control. Designed for real-world use. Deployed in minutes.

lightweight, python based chat ui

This repository provides tutorials and implementations for various Generative AI Agent techniques, from basic to advanced. It serves as a comprehensive guide for building intelligent, interactive A…

The Security Toolkit for LLM Interactions

A framework for comprehensive diagnosis and optimization of agents using simulated, realistic synthetic interactions

Task-Aware Agent-driven Prompt Optimization Framework

A repository consisting of paper/architecture replications of classic/SOTA AI/ML papers in pytorch

🤗 smolagents: a barebones library for agents that think in code.

A high-throughput and memory-efficient inference and serving engine for LLMs

A Python package for converting numbers expressed in natural language to numerical values.

Converts text such as "twenty three" to number/digit "23" in any sentence

Convert number words (eg. twenty one) to numeric digits (21)

The Dataset of NLPCC 2023 (Oral Presentation): Revisit Input Perturbation Problems for LLMs: A Unified Robustness Evaluation Framework for Noisy Slot Filling Task

[USENIX Security 2025] PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models

Repository that accompanies "An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction" (EMNLP 2019)

This repository contains datasets and code for the paper "HINT3: Raising the bar for Intent Detection in the Wild" accepted at EMNLP-2020's Insights Workshop https://insights-workshop.github.io/ Pr…

DSTC11 Track 5 - Task-oriented Conversational Modeling with Subjective Knowledge

DSTC 11 Track 2: Intent Induction from Conversations for Task-Oriented Dialogue

Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]

A framework for prompt tuning using Intent-based Prompt Calibration

An LLM-based autonomous agent controlling real-world applications via RESTful APIs

DSPy: The framework for programming—not prompting—language models

[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

Build resilient language agents as graphs.

NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.