Reverse Dependencies of vllm

The following projects have a declared dependency on vllm:

• nomiracl — Multilingual Relevance Assessment for RAG Applications
• nvidia-lm-eval — A framework for evaluating language models - packaged by NVIDIA
• oat-llm — Online AlignmenT (OAT) for LLMs.
• ochat — An efficient framework for training and serving top-tier, open-source conversational LLMs.
• opencompass — A comprehensive toolkit for large model evaluation
• openmmla-vision — Vision module for the OpenMMLA platform.
• openpo — Build high quality synthetic datasets with AI feedback from 200+ LLMs
• openrlhf — A Ray-based High-performance RLHF framework.
• optimum-benchmark — Optimum-Benchmark is a unified multi-backend utility for benchmarking Transformers, Timm, Diffusers and Sentence-Transformers with full support of Optimum's hardware optimizations & quantization schemes.
• oracle-guardian-ai — Oracle Guardian AI Open Source Project
• orpheus-speech — Orpheus Text-to-Speech System
• oumi — Oumi - Modeling Platform
• outlines — Probabilistic Generative Model Programming
• papertuner — A package for creating ML research assistant models through paper dataset creation and model fine-tuning
• pdf2md-llm — A package to convert PDF files to Markdown using a local LLM.
• pipecat-ai — An open source framework for voice (and multimodal) assistants
• pixano-inference — Deploy inference models served for Artificial Intelligence solutions including but not limited to Pixano.
• plancraft — Plancraft: an evaluation dataset for planning with LLM agents
• promptolution — no summary
• py-data-juicer — A One-Stop Data Processing System for Large Language Models.
• pyragnarok — A package to running RAG models, especially for the TREC 2023 Retrieval Augmented Generation (RAG) track.
• pyText2Sql — Generate SQL queries from natural language
• quest-decoding — A package for sampling from intractable distributions with LLMs.
• rank-llm — A Package for running prompt decoders like RankVicuna
• rankify — A Comprehensive Python Toolkit for Retrieval, Re-Ranking, and Retrieval-Augmented Generation
• refchecker — RefChecker provides automatic checking pipeline for detecting fine-grained hallucinations generated by Large Language Models.
• repoqa — "RepoQA for Evaluating Long-Context Code Understanding"
• rewardbench — Tools for evaluating reward models
• rigging — LLM Interaction Framework
• scandeval — The robust European language model benchmark.
• SciPhi — SciPhi: A Framework for LLM Powered Data.
• search-llm-actions — ('search_llm_actions provides a simple template to collect action trajectories from local (e.g. vllm servers) or remote (e.g. togetherai api) llms by search.',)
• seeme — No-Code/Low Code AI Platform: Innovate. Integrate. Iterate.
• serverless-llm — no summary
• sevals — A framework for evaluating language models
• sglang — SGLang is yet another fast serving framework for large language models and vision language models.
• sglang-router — SGLang is yet another fast serving framework for large language models and vision language models.
• skythought — Skythought Evals: Evaluation and Data Generation Tools for Reasoning Models
• smolagents — 🤗 smolagents: a barebones library for agents. Agents write python code to call tools or orchestrate other agents.
• superduper-vllm — Superduper allows users to work with self-hosted LLM models via [vLLM](https://github.com/vllm-project/vllm).
• superpandas — SuperPandas is a Python library that turbocharges Pandas DataFrames with the power of Generative AI.
• tacc-inf — Efficient LLM inference on Slurm clusters using vLLM (for TACC).
• tail-test — A Toolkit for automatic LLM Evaluation.
• TapeAgents — TapeAgents framework for building, tuning and evaluating LLM Agents
• text2dataset — Easily turn large English text datasets into Japanese text datasets using open LLMs
• text2sql-metadata-filterer — Generate SQL queries from natural language
• text2text — Text2Text Language Modeling Toolkit
• textgrad — no summary
• topicgpt_python — Official implementation of TopicGPT: A Prompt-based Topic Modeling Framework (NAACL'24)
• trl — Train transformer language models with reinforcement learning.
• trust_eval — Metric to measure RAG responses with inline citations
• turbo-alignment — turbo-alignment repository
• txagent — TxAgent: An AI Agent for Therapeutic Reasoning Across a Universe of Tools
• ultravox-vllm — no summary
• univlm — Unified wrapper for HF, VLLM and other models
• vanna — Generate SQL queries from natural language
• vanna-scalegen — Generate SQL queries from natural language
• vec-inf — Efficient LLM inference on Slurm clusters using vLLM.
• verl — verl: Volcano Engine Reinforcement Learning for LLM
• vital-llm-reasoner — Vital LLM Reasoner
• vllm-tgis-adapter — vLLM adapter for a TGIS-compatible grpc server
• weak-annotators — Weak annotators for information extraction (NER)
• wildguard — WildGuard safety classification inference
• xinfer — Framework agnostic computer vision inference. Run 1000+ models by changing only one line of code. Supports models from transformers, timm, ultralytics, vllm, ollama and your custom model.
• xlagent — A lightweight framework for building LLM-based agents
• xverify — Add your description here
• yijian-community — YiJian-Community
• yoneq-text2sql — Generate SQL queries from natural language