J-Space Cognition Suite — a model-agnostic inference-time control suite for deep reasoning, long-horizon work, verification, and recovery. Based on Anthropic's J-space global workspace research.
Repository Index
132,241 visible repositories in the index
217–240 of 748 · Most stars
Metal shaders for SwiftUI.
TokenSpeed is a speed-of-light LLM inference engine.
Official inference repo for FLUX.2 models
The code used to train and run inference with the ColVision models, e.g. ColPali, ColQwen2, and ColSmol.
- colpali
- information-retrieval
- retrieval-augmented-generation
- vision-language-model
Mano-P: Open-source GUI-VLA agent for edge devices. #1 on OSWorld (specialized, 58.2%). Runs locally on Apple M4 Mac mini/MacBook — no data leaves your device.Mano-P 是一个开源 GUI-VLA 项目,支持在 Mac mini/MacBook 上或通过算力棒本地运行推理,实现纯视觉驱动的跨平台 GUI 自动化操作。数据完全本地处理,支持复杂多步骤任务规划与执行。
- computer-use-agents
- desktop-automation
- edge-computing
- gui-automation
Images to inference with no labeling (use foundation models to train supervised models).
- computer-vision
- model-distillation
- auto-labeling
- deep-learning
Stan development repository. The master branch contains the current release. The develop branch contains the latest stable development. See the Developer Process Wiki for details.
- stan
- bayesian-inference
- bayesian
- bayesian-methods
Probabilistic programming with NumPy powered by JAX for autograd and JIT compilation to GPU/TPU/CPU.
- pyro
- jax
- hmc
- inference-algorithms
Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads
Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent, 150k-262k context. vLLM patches, requant pipeline, benchmarks.
- kv-cache
- llm-inference
- local-llm
- quantization
xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism
The fastest way to run Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on a Mac: 125 tok/s in OpenCode on an M5 Max, and a 27B model on 16 GB Macs. Native MTP speculative decoding on Apple Silicon, exact at any temperature. OpenAI and Anthropic compatible local server.
- apple-silicon
- local-ai
- mlx
- mtp
Lightweight Python library for adding real-time multi-object tracking to any detector.
- tracking
- tracking-algorithm
- kalman-filter
- object-tracking
SNIPER / AutoFocus is an efficient multi-scale object detection training / inference algorithm
Building a Neural Network-Native Engine (3N). Python authoring, C++ runtime, Vulkan/WebGPU. Windows, Linux, Android and Web.
- editor
- game-engine
- physics
- python
Fast ML inference & training for ONNX models in Rust
- ai
- inference
- machine-learning
- onnxruntime
cubestudio开源云原生一站式机器学习/深度学习/大模型AI平台/MaaS/mlops/人工智能平台/训推平台,算法全链路流程,多租户,算力租赁平台,token中转,拖拉拽任务流pipeline编排,多机多卡分布式训练,超参搜索,推理服务,VGPU虚拟化,云边端协同,边缘计算,自动化标注平台,deepseek等大模型sft微调/奖励模型/强化学习训练,vllm/ollama/mindie大模型多机推理,私有知识库llmops智能体,AI模型市场,支持国产异构算力调度,昇腾/寒武纪/海光/摩尔/沐曦等,支持ib/roce/RDMA,信创支持
Use Hugging Face with JavaScript
An open coding agent for your terminal, built by a community collective rather than a company. Bring your own model, keep your code on your machine, and owe nothing to anyone.
Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).
- large-language-models
- llm-inference
- speculative-decoding
Run the full 2.78-trillion-parameter Kimi K3 model, DeepSeek V4.1 Flash or GLM-5.3-Flash beyond available RAM by streaming activated weights directly from NVMe. A dependency-free, embeddable C inference engine.
Deep Learning Server and CLI for Torch and TensorRT
Rule engine implementation in Golang
- golang
- rule-engine
- rule
- inference-engine