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
111,821 visible repositories in the index
121–144 of 315 · Most stars
The code used to train and run inference with the ColVision models, e.g. ColPali, ColQwen2, and ColSmol.
Images to inference with no labeling (use foundation models to train supervised models).
Probabilistic programming with NumPy powered by JAX for autograd and JIT compilation to GPU/TPU/CPU.
xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism
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.
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.
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
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.
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.
Turn any computer or edge device into a command center for your computer vision projects.
Open source video conferencing app powered by LiveKit. Built with Django and React.
Executable file for VITS inference
The repository host gives no description.
An agentic company research tool powered by LangGraph and Tavily that conducts deep diligence on companies using a multi-agent framework. It leverages OpenRouter on the backend for rapid inference with any leading model.
A unified orchestration layer for heterogeneous AI compute. It standardizes how to manage compute and run training and inference on GPU clouds, Kubernetes, VMs, or bare-metal clusters.
micronet, a model compression and deploy lib. compression: 1、quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference)、Low-Bit(≤2b)/Ternary and Binary(TWN/BNN/XNOR-Net); post-training-quantization(PTQ), 8-bit(tensorrt); 2、 pruning: normal、regular and group convolutional channel pruning; 3、 group convolution structure; 4、batch-normalization fuse for quantization. deploy: tensorrt, fp32/fp16/int8(ptq-calibration)、op-adapt(upsample)、dynamic_shape
Communicate with an LLM provider using a single interface
收录NLP竞赛策略实现、各任务baseline、相关竞赛经验贴(当前赛事、往期赛事、训练赛)、NLP会议时间、常用自媒体、GPU推荐等,持续更新中
Code, labs, and resources for O'Reilly AI Systems Performance Engineering: GPU optimization, distributed training, inference scaling, and full-stack tuning.
A probabilistic programming library for Bayesian deep learning, generative models, based on Tensorflow