HumanEvalHumanEval is OpenAI's open-source benchmark of 164 hand-written Python problems for evaluating large language models on code generation using functional correctness.(0)0
ONNX RuntimeONNX Runtime is Microsoft's open-source AI engine for accelerated machine learning inference and training across cloud, edge, mobile, and web platforms.(0)0
OpenVINOOpenVINO is Intel's open-source toolkit for converting, optimizing, and deploying AI models across CPUs, GPUs, and NPUs with production-ready model serving.(0)0
Text Generation WebUIRun large language models locally with Text Generation WebUI — supports text, vision, tool-calling, and fine-tuning. 100% offline, open source, and private.(0)0
M Marian NMTMarian NMT is an efficient, open-source neural machine translation framework written in pure C++. Supports Transformer and RNN architectures with multi-GPU training, developed by Microsoft Translator.(0)0
vLLMvLLM is an open-source high-throughput LLM inference library supporting GPU, CPU, and TPU backends with an OpenAI-compatible API, PagedAttention, and production deployment tools.(0)0
MT BenchMT Bench is an open-source multi-turn benchmark for evaluating large language models using GPT-4 as an automated judge. Part of the FastChat ecosystem by lm-sys.(0)0
FastChatFastChat is an open-source platform for training, serving, and evaluating large language models. Powers Chatbot Arena with OpenAI-compatible APIs and a distributed multi-model serving system.(0)0
CandleCandle is an open-source, minimalist ML framework for Rust with GPU support, built by Hugging Face. Run LLMs, Whisper, YOLO, and more with high performance.(0)0
TensorFlow LiteLiteRT (formerly TensorFlow Lite) is Google's open-source framework for deploying ML and GenAI models on Android, iOS, web, desktop, and IoT devices with GPU/NPU acceleration.(0)0
