Repo AI đang lênCập nhật hằng ngày từ GitHub
Repo AI, lập trình & video AI xếp theo tốc độ tăng sao.
Repo AI, lập trình & video AI xếp theo tốc độ tăng sao.
| # | Repo | Sao | 7 ngày |
|---|---|---|---|
| 151 | MU | 818 | — |
| 152 | CY | 813 | — |
| 153 | WA | 811 | — |
| 154 | AD | 807 | — |
| 155 | SE serizba/cppflow Run TensorFlow models in C++ without installation and without Bazel Suy luận & chạy LLM cục bộ | 800 | — |
| 156 | NA nace-ai/kapitsa Blazing fast Apple Silicon inference engine optimized for Qwen & Nemotron. OpenAI + Anthropic API compatible. Built by folks from nace.ai Suy luận & chạy LLM cục bộ | 780 | — |
| 157 | H2 h2non/filetype.py Small, dependency-free, fast Python package to infer binary file types checking the magic numbers signature Suy luận & chạy LLM cục bộ | 779 | — |
| 158 | EM emlearn/emlearn Machine Learning inference engine for Microcontrollers and Embedded devices Suy luận & chạy LLM cục bộ | 775 | — |
| 159 | AW aws/studio-lab-examples Example notebooks for working with SageMaker Studio Lab. Sign up for an account at the link below! Suy luận & chạy LLM cục bộ | 774 | — |
| 160 | CS | 769 | — |
| 161 | TE tetherto/qvac Open-source local AI SDK - run AI on-device with no cloud, no API keys. Supports GGUF, RAG, image, music, and video generation, speech-to-text, P2P inference, and more. Cross-platform: Linux, macOS, Windows, Android, iOS. Suy luận & chạy LLM cục bộ | 763 | — |
| 162 | ST | 758 | — |
| 163 | TO tobegit3hub/simple_tensorflow_serving Generic and easy-to-use serving service for machine learning models Suy luận & chạy LLM cục bộ | 756 | — |
| 164 | HI hidet-org/hidet(lưu trữ) An open-source efficient deep learning framework/compiler, written in python. Suy luận & chạy LLM cục bộ | 743 | — |
| 165 | V- v-modal/awesome-jev-tools A curated list of tools built for Jev — TypeSafe AI's System One model for typed decisions. Suy luận & chạy LLM cục bộ | 735 | — |
| 166 | IN intel/ai-reference-models(lưu trữ) Intel® AI Reference Models: contains Intel optimizations for running deep learning workloads on Intel® Xeon® Scalable processors and Intel® Data Center GPUs Suy luận & chạy LLM cục bộ | 731 | — |
| 167 | PR privacytrustlab/ml_privacy_meter Privacy Meter: An open-source library to audit data privacy in statistical and machine learning algorithms. Suy luận & chạy LLM cục bộ | 731 | — |
| 168 | ZH zhiqwang/yolort yolort is a runtime stack for yolov5 on specialized accelerators such as tensorrt, libtorch, onnxruntime, tvm and ncnn. Suy luận & chạy LLM cục bộ | 730 | — |
| 169 | HA hailo-ai/hailo_model_zoo The Hailo Model Zoo includes pre-trained models and a full building and evaluation environment Suy luận & chạy LLM cục bộ | 724 | — |
| 170 | FU fudan-generative-vision/Remory Remory: Learning Residual Memory for Context Compaction Suy luận & chạy LLM cục bộ | 723 | — |
| 171 | AV | 717 | — |
| 172 | PR prabanta-dev/janas 37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs 2.8 for llama.cpp; reading 62 vs 16 tok/s. Faster than llama.cpp on all 13 models compared in Q4_K_M. LLMs bigger than your RAM, pure C, CPU or GPU. Suy luận & chạy LLM cục bộ | 710 | — |
| 173 | FE feifeibear/long-context-attention USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference Suy luận & chạy LLM cục bộ | 697 | — |
| 174 | NV NVIDIA-AI-IOT/tf_trt_models TensorFlow models accelerated with NVIDIA TensorRT Suy luận & chạy LLM cục bộ | 696 | — |
| 175 | DE DerwenAI/kglab Graph Data Science: an abstraction layer in Python for building knowledge graphs, integrated with popular graph libraries – atop Pandas, NetworkX, RAPIDS, RDFlib, pySHACL, PyVis, morph-kgc, pslpython, pyarrow, etc. Suy luận & chạy LLM cục bộ | 696 | — |
| 176 | KO kossisoroyce/timber Ollama for classical ML models. AOT compiler that turns XGBoost, LightGBM, scikit-learn, CatBoost & ONNX models into native C99 inference code. One command to load, one command to serve. 336x faster than Python inference. Suy luận & chạy LLM cục bộ | 691 | — |
| 177 | DE | 680 | — |
| 178 | CA carloslfu/slotstream Run a 105 GB AI model on a Mac that can't hold it. Qwen3.8-Flash-Next 4-bit, streamed from SSD on 16–64 GB Apple Silicon Macs. Fully native Swift, MLX and Metal. Offline, no Python. CLI, Swift library, and Ollama/OpenAI/Anthropic APIs. Works with Claude Code and Codex. Suy luận & chạy LLM cục bộ | 671 | — |
| 179 | MO | 668 | — |
| 180 | OW | 667 | — |
| 181 | RU run-ai/genv(lưu trữ) GPU environment and cluster management with LLM support Suy luận & chạy LLM cục bộ | 659 | — |
| 182 | XB xboot/libonnx A lightweight, portable pure C99 onnx inference engine for embedded devices with hardware acceleration support. Suy luận & chạy LLM cục bộ | 656 | — |
| 183 | SF SforAiDl/KD_Lib A Pytorch Knowledge Distillation library for benchmarking and extending works in the domains of Knowledge Distillation, Pruning, and Quantization. Suy luận & chạy LLM cục bộ | 651 | — |
| 184 | PA ParisNeo/lollms_hub A proxy server for multiple ollama instances with Key security Suy luận & chạy LLM cục bộ | 649 | — |
| 185 | OP open-edge-platform/dlstreamer Deep Learning Streamer (DL Streamer) Pipeline Framework is an open-source streaming media analytics framework, based on GStreamer* multimedia framework, for creating complex media analytics pipelines for the Cloud or at the Edge. Suy luận & chạy LLM cục bộ | 649 | — |
| 186 | NE Nehanth/pooled Peer-to-peer LLM inference in the browser: pool your devices to run big open models, for chat and coding agents. Suy luận & chạy LLM cục bộ | 647 | — |
| 187 | ZE | 643 | — |
| 188 | WA WaveSpeedAI/waverless High-performance serverless GPU task orchestration — the scheduling layer behind wavespeed.ai Suy luận & chạy LLM cục bộ | 634 | — |
| 189 | NI NightMean/OlliteRT Turn your Android phone into an OpenAI-compatible LLM inference server - Fully local, private and Open Source Suy luận & chạy LLM cục bộ | 631 | — |
| 190 | TH therealoliver/Deepdive-llama3-from-scratch Achieve the llama3 inference step-by-step, grasp the core concepts, master the process derivation, implement the code. Suy luận & chạy LLM cục bộ | 629 | — |
| 191 | JM jmerelnyc/Talos GPU worker client for the Talos network. Pairs with your Talos account, serves open-model inference jobs over a WebSocket, and reports uptime for payouts. Suy luận & chạy LLM cục bộ | 629 | — |
| 192 | SE | 620 | — |
| 193 | SL slavabarkov/tidy Offline semantic Text-to-Image and Image-to-Image search on Android powered by quantized state-of-the-art vision-language pretrained CLIP model and ONNX Runtime inference engine Suy luận & chạy LLM cục bộ | 609 | — |
| 194 | JA jaylfc/taOS Self-hosted AI agent OS. Your memory, chat, agents, and files stay on hardware you own, offline by default, cloud by choice. Offline AI memory (taOSmd), self-hosted multi-framework group chat, a full web desktop + app store, and auto-clustering across the consumer hardware you already have (Orange/Raspberry Pi, Mac mini, gaming PC). Suy luận & chạy LLM cục bộ | 607 | — |
| 195 | OT | 595 | — |
| 196 | GR grimoire/mmdetection-to-tensorrt convert mmdetection model to tensorrt, support fp16, int8, batch input, dynamic shape etc. Suy luận & chạy LLM cục bộ | 595 | — |
| 197 | KI Ki6an/fastT5 ⚡ boost inference speed of T5 models by 5x & reduce the model size by 3x. Suy luận & chạy LLM cục bộ | 587 | — |
| 198 | KA kac89/vulnrepo VULNRΞPO - Free vulnerability report generator and repository, end-to-end encrypted! Templates of issues, CWE,CVE,MITRE ATT&CK,PCI DSS, import Nmap/Nessus/Burp/OpenVAS/Bugcrowd/Trivy, Jira export, TXT/JSON/MARKDOWN/HTML/DOCX, attachments, automatic changelog, stats, vulnerability management, bugbounty, local ai/llm, super fast pentest reporting! Suy luận & chạy LLM cục bộ | 585 | — |
| 199 | GO google/qkeras QKeras: a quantization deep learning library for Tensorflow Keras Suy luận & chạy LLM cục bộ | 584 | — |
| 200 | DE DerryHub/BEVFormer_tensorrt BEVFormer inference on TensorRT, including INT8 Quantization and Custom TensorRT Plugins (float/half/half2/int8). Suy luận & chạy LLM cục bộ | 583 | — |