A vLLM-style inference server for Apple Silicon with a native MLX backend, exposing both OpenAI and Anthropic compatible APIs in a single process, featuring multimodal unified serving, continuous batching, paged KV cache, and SSD-tiered caching.
A local AI inference engine for Apple Silicon with OpenAI-compatible API, supporting multi-modal, tool calling, and smart cloud routing.
An advanced post-training quantization toolkit for LLMs and VLMs by Intel, leveraging SignRound optimization to support 2–4 bit weight quantization and automatic mixed-precision scheme generation across Intel CPU/GPU, NVIDIA GPU, and Habana Gaudi.
A fully disaggregated multimodal model inference and serving framework that extends vLLM to support any-to-any modality unified inference and high-performance deployment.
A high-performance OpenAI-compatible API server for MLX models on Apple Silicon, supporting text, vision, audio transcription, and image generation/editing.
Flexible and scalable reinforcement learning training infrastructure for embodied and agentic AI post-training, decoupling logical workflow composition from efficient physical execution via the M2Flow paradigm.
A plug-and-play multi-object tracking (MOT) Python library offering modular implementations of classic algorithms like SORT and ByteTrack. Features a detector-agnostic design compatible with any object detection model (YOLO, DETR, etc.), supporting video files, cameras, RTSP streams, and more. Provides unified CLI tools and Python API with built-in evaluation metrics (CLEAR, HOTA, Identity).
An end-to-side omnimodal LLM by Tsinghua THUNLP supporting vision, speech, and full-duplex multimodal live streaming, optimized for mobile deployment with performance rivaling Gemini 2.5 Flash.
An open-source framework by Stream for building vision AI agents that work with any model or video provider, leveraging Stream's edge network for ultra-low latency video experiences.
A customizable AI desktop companion project with character settings, voice conversations, long-term memory capabilities, and sub-1-second response times. Integrates with Live2D models for visual presentation.
Page 1 / 3 · 22 total
Get the latest AI tools and trends delivered straight to your inbox. No spam, just intelligence.
