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
llama.cppRun large language models locally with llama.cpp — a high-performance, open-source C/C++ inference engine supporting CUDA, Metal, Vulkan, and GGUF quantization for 50+ model architectures.(0)0
ZenMLZenML is an open-source AI control plane for orchestrating ML pipelines and LLM agent workflows with automated versioning, infrastructure abstraction, and governance from local to Kubernetes.(0)0
G Garakgarak is an open-source LLM vulnerability scanner with dozens of plugins and thousands of prompts that test large language model security, backed by NVIDIA.(0)0
PrimateAIPrimateAI is an open-source deep residual neural network by Illumina that scores the pathogenicity of missense variants using primate sequence data.(0)0
Intel Neural CompressorOpen source Python library by Intel for framework-independent AI model optimization via quantization, pruning, and knowledge distillation.(0)0
EZKLEZKL is the only audited zero-knowledge proof library for AI. Detect tampering, GPU failures, and corrupted outputs in production with pure software, Intel TEE, or NVIDIA CUDA support.(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
LlamafileLlamafile by Mozilla lets you distribute and run large language models as a single portable executable on macOS, Linux, and Windows — no setup required.(0)0
MACE FoundationsMACE is an open-source ML framework for generating accurate force fields using equivariant message passing. Supports foundation models, fine-tuning, LAMMPS, and OpenMM.(0)0
