Reference client for Bitmessage: a P2P encrypted decentralised communication protocol:
- bitmessage
- pybitmessage
- p2p-communication-protocol
- python
108,094 visible repositories in the index
193–216 of 687 · Most stars
Reference client for Bitmessage: a P2P encrypted decentralised communication protocol:
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.
A Unified Library for Parameter-Efficient and Modular Transfer Learning
Images to inference with no labeling (use foundation models to train supervised models).
TensorFlow Graphics: Differentiable Graphics Layers for TensorFlow
Probabilistic programming with NumPy powered by JAX for autograd and JIT compilation to GPU/TPU/CPU.
Learning Chinese Character style with conditional GAN
xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism
Reference implementation of the Transformer architecture optimized for Apple Neural Engine (ANE)
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.
vLLM’s reference system for K8S-native cluster-wide deployment with community-driven performance optimization
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.
Real-time end-to-end singing voice conversion system based on DDSP (Differentiable Digital Signal Processing)
A unified framework for privacy-preserving data analysis and machine learning
Lightweight Python library for adding real-time multi-object tracking to any detector.
SNIPER / AutoFocus is an efficient multi-scale object detection training / inference algorithm
A Calibre plugin to translate ebook into a specified language.
A comfortable and well-configurable graphical Frontend for incremental backups, with a command-line version also available. Modified files are transferred, while unchanged files are linked to the new folder using rsync's hard link feature, saving storage space. Restoring is straightforward via file manager, command line or Back In Time itself.
Open-source, self-hostable social media management platform. Schedule, publish, and manage content across 10+ platforms from a single dashboard. Free alternative to Buffer, Sendible, and SocialPilot.
Building a Neural Network-Native Engine (3N). Python authoring, C++ runtime, Vulkan/WebGPU. Windows, Linux, Android and Web.
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
Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).
Ticket shop application for conferences, festivals, concerts, tech events, shows, exhibitions, workshops, barcamps, etc.