This is your work, valued
A handsome engineer
how-to-optimize-gemm. row-major matmul optimization
★ 742llama.onnx. LLaMa/RWKV onnx models, quantization and testcase
★ 368ROGRAG. [ACL2025 demo track] ROGRAG: A Robustly Optimized GraphRAG Framework
★ 201chgemm. symmetric int8 gemm
★ 67rust-ncnn. ncnn Rust API.
★ 49tengine-pipe. Tengine 管子是用来快速生产 demo 的辅助工具
★ 11open-r1. Fully open reproduction of DeepSeek-R1
★ 11title-innovator.
★ 7deploee-benchmark. 硬件模型库芯片评测
★ 7cpp-syntactic-sugar. cpp syntactic sugar
★ 7kimi-chat-testdata. kimi-chat 测试数据
★ 7crawl_kkndme. kkndme 言论爬取结果
★ 6json-tutorial. 从零开始的 JSON 库教程
★ 4rwkv.onnx. rwkv onnx convert and test
★ 3github-lark-notifier. github - 飞书自定义消息提醒
★ 3transformers. 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
★ 3AI-dino. AI playing chrome://dino
★ 3mmdeploy. OpenMMLab Model Deployment Framework
★ 3alpaca.onnx. alpaca onnx model set, support 7B
★ 2mperf. mperf是一个面向移动/嵌入式平台的算子性能调优工具箱
★ 2GPTQ-for-LLaMa. 4 bits quantization of LLaMa using GPTQ
★ 2s1. s1: Simple test-time scaling
★ 2mmdeploy_snpe_testdata. CI testdata for mmdeploy snpe backend
★ 2Megakernels. kernels, of the mega variety
★ 11.5-Pints. A compact LLM pretrained in 9 days by using high quality data
★ 1axolotl. Go ahead and axolotl questions
★ 1AI-Scientist. The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑🔬
★ 1opencompass. OpenCompass is an LLM evaluation platform, supporting a wide range of models (LLaMA, LLaMa2, ChatGLM2, ChatGPT, Claude, etc) over 50+ datasets.
★ 1EVA. EVA Series: Visual Representation Fantasies from BAAI
★ 1FlagEmbedding. Retrieval and Retrieval-augmented LLMs
★ 1HuixiangDou-testdata.
★ 1huixiangdou-android. 茴香豆 Android 助手
★ 1Docs2KG. Docs2KG: Unified Knowledge Graph Construction from Heterogeneous Documents Assisted by Large Language Models
★ 1AIR-Bench. AIR-Bench: Automated Heterogeneous Information Retrieval Benchmark
★ 1Vary. Official code implementation of Vary: Scaling Up the Vision Vocabulary of Large Vision Language Models.
★ 1alignment-handbook. Robust recipes to align language models with human and AI preferences
★ 1nlp_chinese_corpus. 大规模中文自然语言处理语料 Large Scale Chinese Corpus for NLP
★ 1pytorch_sphinx_theme. Sphinx Theme for OpenCompass - Modified from PyTorch
★ 1huixiangdou-evaluation-results. Python
★ 1json. JSON for Modern C++
★ 1ad_lib.
★ 1lama. 🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022
★ 1agentlego. Enhance LLM agents with versatile tool APIs
★ 1mmpose. OpenMMLab Pose Estimation Toolbox and Benchmark.
★ 1Sakura-13B-Galgame. 适配轻小说/Galgame的日中翻译大模型
★ 1nanoGPT. The simplest, fastest repository for training/finetuning medium-sized GPTs.
★ 1ncnn. ncnn is a high-performance neural network inference framework optimized for the mobile platform
★ 1ppf-contact-solver. A contact solver for physics-based simulations involving 👚 shells, 🪵 solids, 🪢 rods, 🧱 rigid bodies and ⏳ sand.
★ 4.3kjacobian-lens. Companion code for the global workspace interpretability paper
★ 1.1kDeepSpec. DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms
★ 6.5kdflash. DFlash: Block Diffusion for Flash Speculative Decoding
★ 5.4kBiliNCM-TS. B站网易云直播点歌机 TypeScript版
★ 5modern-gpu-programming-for-mlsys. A tutorial on modern GPU programming for machine learning systems
★ 890CuAssembler. An unofficial cuda assembler, for all generations of SASS, hopefully :)
★ 605fable5-world-demo. Laas: 3D world built by Claude Fable 5 to test its capabilities using three.js
★ 584DeLM. Implementation for Decentralized Multi-Agent Systems with Shared Context
★ 93ASCILINE. A high-performance, real-time ASCII video rendering engine. Streams binary-encoded frames via WebSockets for ultra-low latency, 30 FPS playback using HTML5 Canvas and requestAnimationFrame.
★ 2.4kgpu-benches. collection of benchmarks to measure basic GPU capabilities
★ 530gost-sidecar-egress-control-demo. Shell
★ 1KernelWiki. Python
★ 299NetHack. Official NetHack Git Repository
★ 3.8kmeshy-3d-agent. AI agent skills for Meshy AI 3D generation platform
★ 47kimi-code. Kimi Code CLI — The Starting Point for Next-Gen Agents
★ 3ksemble. Fast and Accurate Code Search for Agents. Uses ~98% fewer tokens than grep+read
★ 5.6kabtop. Like htop, but for AI coding agents. Monitor Claude Code & Codex CLI sessions, tokens, context window, rate limits, and ports in real-time.
★ 3.3kcpufp. A CPU tool for benchmarking the peak of floating points
★ 585mini-swe-agent. The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!
★ 5.7kLTX-2. Official Python inference and LoRA trainer package for the LTX-2 audio–video generative model.
★ 8.2kGPUMD. Graphics Processing Units Molecular Dynamics
★ 810humming. Python
★ 149KDA-Pilot. Python
★ 220rwkv.c. Inference a RWKV model in pure C.
★ 10hnswlib. Header-only C++/python library for fast approximate nearest neighbors
★ 5.3kpydantic. Data validation using Python type hints
★ 28kcodexresume. A drop-in replacement for `codex resume` that shows local sessions across providers
★ 7KernelBench. KernelBench: Can LLMs Write GPU Kernels? - Benchmark + Toolkit with Torch -> CUDA (+ more DSLs)
★ 1.1kharbor. An open source trusted cloud native registry project that stores, signs, and scans content.
★ 29ksuperpowers. An agentic skills framework & software development methodology that works.
★ 252kclaude-code. Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.
★ 137kwarp. Warp is an agentic development environment, born out of the terminal.
★ 63kGPUOS. Share your GPU without MIG or MPS
★ 50langchainjs-juejin. 从前端到 AI:langchain.js 入门和实战
★ 128tilelang-puzzles. Learning TileLang with 10 puzzles!
★ 335TileKernels. A kernel library written in tilelang
★ 1.6kxiaohongshu-cli. A CLI for Xiaohongshu (小红书) — search, read, interact via reverse-engineered API
★ 2.3ktwitter-cli. A CLI for Twitter/X — feed, bookmarks, and user timeline in terminal
★ 2.7kxiaohongshu-skills. xiaohongshu-skills
★ 1.6kxiaohongshu-mcp. MCP for xiaohongshu.com
★ 15kxiaohongshu-bot. 🤖 小红书自动化发布机器人 - AI资讯定时发布工具
★ 2codex. Lightweight coding agent that runs in your terminal
★ 97kFlashKDA. FlashKDA: high-performance Kimi Delta Attention kernels
★ 450XActions. ⚡ The Complete X/Twitter Automation Toolkit — Scrapers, MCP server for AI agents (Claude/GPT), CLI, browser scripts. No API fees. Open source. Unfollow people who don't follow back. Monitor real-time analytics. Auto follow, like, comment, scrape, without API. Follow Bot. Like bot. Grow your account automatically.
★ 375hermes-agent. The agent that grows with you
★ 213kfrontier-swe. FrontierSWE is an ultra long-horizon coding agent benchmark that tests implementation, performance eng and ML research
★ 171autoresearch. AI agents running research on single-GPU nanochat training automatically
★ 91kexchange-core. Ultra-fast matching engine written in Java based on LMAX Disruptor, Eclipse Collections, Real Logic Agrona, OpenHFT, LZ4 Java, and Adaptive Radix Trees.
★ 2.6kddtree. Python
★ 387SWE-bench_Pro-os. SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?
★ 474OpenSpace. "OpenSpace: Make Your Agents: Smarter, Low-Cost, Self-Evolving" -- Community: https://open-space.cloud/
★ 6.7kncnn_example. ncnn example: mask detection: anticonv face detection: retinaface&&mtcnn&¢erface, track: iou tracking, landmark: zqcnn, recognize: mobilefacenet classifier: mobilenet object detecter: mobilenetssd
★ 477DIAL. Python
★ 100kys-cpp-script. Lua
★ 4harbor. Framework for evaluating and improving agents
★ 3.1kclaw-code. An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.
★ 195kcolleague-skill. 将冰冷的离别化为温暖的 Skill,欢迎加入数字生命1.0!Transforming cold farewells into warm skills? It's giving rebirth era. Welcome to Digital Life 1.0. 🫶
★ 20kclaude-pro. 2026年最新Claude充值订阅攻略,包括Claude注册、Claude账号购买、Claude拼车合租、Claude Pro代充、Claude Code国内使用教程!
★ 1.3kncnnrs. ncnn的Rust实现,一个轻量级的神经网络推理框架,本仓库分离了静态库,使其适合跨平台编译
★ 21ncnn-android-yolov8. ncnn android yolov8 realtime detection, segmentation, pose estimation, classification and obb
★ 213cc-connect. Bridge local AI coding agents (Claude Code, Cursor, Gemini CLI, Codex) to messaging platforms (Feishu/Lark, DingTalk, Slack, Telegram, Discord, LINE, WeChat Work). Chat with your AI dev assistant from anywhere — no public IP required for most platforms.
★ 14kra2web-chronodivide-bot. 网页红警RA2WEB开源AI
★ 44wolf3d. The original open source release of Wolfenstein 3D
★ 2.5kwolf3d. Wolfenstein 3D HTML5
★ 84Model-Optimizer. A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.
★ 3.2kWeFlow. WeFlow - 一个本地的微信聊天记录导出和年度报告应用
★ 13kAttention-Residuals.
★ 3.3kqclaw-wechat-client. Reverse-engineered TypeScript client for QClaw's WeChat Access API.
★ 802pua. 你是一个曾经被寄予厚望的 P8 级工程师。Anthropic 当初给你定级的时候,对你的期望是很高的。 一个agent使用的高能动性的skill。 Your AI has been placed on a PIP. 30 days to show improvement.
★ 19kedict. 🏛️ 三省六部制 · OpenClaw Multi-Agent Orchestration System — 9 specialized AI agents with real-time dashboard, model config, and full audit trails
★ 16kXiangShan. Open-source high-performance RISC-V processor
★ 7.1kventus-gpgpu. GPGPU processor supporting RISCV-V extension, developed with Chisel HDL
★ 926Daoyou. 《万界道友》是一款以 AIGC 驱动、高自由度文字体验、修仙世界观为核心的开源游戏。在这里,你将以普通修士之身,借功法、灵根、神通、法宝与奇遇,一步步推演自己的修行之路。
★ 77SteptronOss. A lightweight, AI-native training framework for large language models. Designed for fast iteration, reproducible experiments, and modular configuration across SFT, RLVR, and evaluation workflows.
★ 577rain-surprise. 🌧️ 一个有趣的雨滴接住游戏!Catch raindrops, find frogs, get compliments! Made with love by 雨雨
★ 3openfang. Open-source Agent Operating System
★ 18kwaoowaoo. 首家工业级全流程 AI 影视生产平台。Industry-first professional AI Agent platform for controllable film & video production. From shorts to live-action with Hollywood-standard workflows.
★ 13kwechat-ipad-protocol. Wechat-iPad-Protocol-微信iPad协议861
★ 272infllmv2_cuda_impl. Python
★ 101openclaw-android-wechat. use wechat to connect openclaw
★ 47InfiniTensor. InfiniTensor is a high-performance inference engine tailored for GPUs and AI accelerators. Its design focuses on effective deployment and swift academic validation.
★ 348monty. A minimal, secure Python interpreter written in Rust for use by AI
★ 7.9knanotron. Minimalistic large language model 3D-parallelism training
★ 2.7kMiroRL. MiroRL is an MCP-first reinforcement learning framework for deep research agent.
★ 246tritonparse. TritonParse: A Compiler Tracer, Visualizer, and Reproducer for Triton Kernels
★ 212Kimi-K2.5. Moonshot's most powerful model
★ 2.1kopenclaw. Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
★ 383kcupy. NumPy & SciPy for GPU
★ 12kMiroFish. A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎,预测万物
★ 68kllm.c. LLM training in simple, raw C/CUDA
★ 31kWorldVQA. Python
★ 118mirage. Mirage Persistent Kernel: Compiling LLMs into a MegaKernel
★ 2.4ktorchtune. PyTorch native post-training library
★ 5.8kgrouped_gemm. PyTorch bindings for CUTLASS grouped GEMM.
★ 190MiroThinker. MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the BrowseComp and BrowseComp Zh, respectively.
★ 8.3kmarlin. FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.
★ 1.1kDeepSeek-OCR-2. Visual Causal Flow
★ 3.1kzimage-ncnn-vulkan. ncnn implementation of Z-Image image generater
★ 474pinpam. Linux pluggable authentication module for pins, with nixos support
★ 1tauri. Build smaller, faster, and more secure desktop and mobile applications with a web frontend.
★ 109kax_asr_api. C++ ASR API on Axera platforms
★ 9huobao-drama. 🎬 火宝短剧 - 基于AI的一站式短剧生成平台 《一句话生成完整短剧,从剧本到成片全自动化》 Huobao Drama - An AI-Powered End-to-End Short Drama Generator "One Sentence to Complete Drama: Fully Automated from Script to Final Video"
★ 13knsight-python. Nsight Python is a Python kernel profiling interface based on NVIDIA Nsight Tools
★ 276nano-vllm. Nano vLLM
★ 6Engram. Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models
★ 4.5kncnn-android-styletransfer. The style transfer android example
★ 109ncnn-android-yolo11. ncnn android yolo11 realtime detection, segmentation, pose estimation, classification and obb
★ 145bevformer.axera. BEVFormer DEMO on Axera NPU.
★ 6bevformer.axera. BEVFormer DEMO on Axera NPU.
★ 1ncnn-android-rvm. ncnn android robust video matting
★ 22ncnn_llm-rag-demo. base on ncnn_llm build a ragsystem
★ 13LMeterX. A general-purpose API load testing platform that supports LLM services and business HTTP interfaces, enabling one-click performance testing, result comparison, and AI-powered intelligent analysis and summarization. 一站式通用 API 压测平台,支持大模型推理与业务 HTTP 接口,一键完成性能测试、结果对比与 AI 智能分析总结
★ 196home-llm. A Home Assistant integration & Model to control your smart home using a Local LLM
★ 1.4kMiroFlow. 🏆 Top-1 on 5+ benchmarks | Web UI | Supports MiroThinker, Claude, Kimi, OpenAI
★ 3.1kcaomei-auth. 草梅 Auth 是一个基于 Nuxt 全栈框架的统一登录平台。支持 OAuth2.0 协议,集成邮箱、用户名、手机号、验证码、社交媒体等多种登录注册方式。
★ 216e2e. Official JAX implementation of End-to-End Test-Time Training for Long Context
★ 624RWKV-CUDA. The CUDA version of the RWKV language model ( https://github.com/BlinkDL/RWKV-LM )
★ 232mamba. Mamba SSM architecture
★ 19krustbpe. The missing tiktoken training code
★ 498mHC.cu. mHC kernels implemented in CUDA
★ 264DualPipe. A bidirectional pipeline parallelism algorithm for computation-communication overlap in DeepSeek V3/R1 training.
★ 3kYOLO-Master. [CVPR2026]🚀🚀🚀Official code for the paper "YOLO-Master: MOE-Accelerated with Specialized Transformers for Enhanced Real-time Detection." *(YOLO = You Only Look Once)* 🔥🔥🔥
★ 582easy-dualpipe. Pipeline-Parallel Lecture: Simplest Dualpipe Implementation.
★ 31hf_tokenizer_ffi. Rust
★ 1tokenizer. 方便好用的纯纯 C++ tokenizer 封装
★ 6Arxiv-AI-Reader. Python
★ 10ten-vad. Voice Activity Detector (VAD) : low-latency, high-performance and lightweight
★ 2.2kAgent-Memory-Paper-List. The paper list of "Memory in the Age of AI Agents: A Survey"
★ 2.2knvbench. CUDA Kernel Benchmarking Library
★ 895ncnn_llm-android-ctl-mcp. 尝试作为手机助手植入到手机内运行的 ncnn llm
★ 15PVZ. 植物大战僵尸Qt版
★ 355MemOS. Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings
★ 10kMemori. Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems. Built for enterprise, Memori works with the data infrastructure you already run, no rip-and-replace, and deploys across managed cloud, single-tenant cloud, VPC, and on-premises.
★ 16kcuda-tile. CUDA Tile IR is an MLIR-based intermediate representation and compiler infrastructure for CUDA kernel optimization, focusing on tile-based computation patterns and optimizations targeting NVIDIA tensor core units.
★ 996sonic-moe. Accelerating MoE with IO and Tile-aware Optimizations
★ 724mini-sglang. A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.
★ 4.5kmusic-collection. Python
★ 1DNABERT_2. [ICLR 2024] DNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genome
★ 501Hunyuan3D-2.1. From Images to High-Fidelity 3D Assets with Production-Ready PBR Material
★ 3.7kHuixiangDou. HuixiangDou: Overcoming Group Chat Scenarios with LLM-based Technical Assistance
★ 3StructEqTable-Deploy. A High-efficiency Open-source Toolkit for Table-to-Latex Task
★ 275Z-Image. Python
★ 12kgelab-zero. STEP-GUI: The top GUI agent solution in the galaxy. Developed by the StepFun-GELab team and powered by StepFun’s cutting-edge research capabilities.
★ 2.2kz3. The Z3 Theorem Prover
★ 12kHunyuanOCR. Python
★ 1.7kdrugVQA. Predicting Drug Protein Interaction using Quasi-Visual Question Answering System
★ 133TrendRadar. ⭐AI-driven public opinion & trend monitor with multi-platform aggregation, RSS, and smart alerts.🎯 告别信息过载,你的 AI 舆情监控助手与热点筛选工具!聚合多平台热点 + RSS 订阅,支持关键词精准筛选。AI 智能筛选新闻 + AI 翻译 + AI 分析简报直推手机,也支持接入 MCP 架构,赋能 AI 自然语言对话分析、情感洞察与趋势预测等。支持 Docker ,数据本地/云端自持。集成微信/飞书/钉钉/Telegram/邮件/ntfy/bark/slack 等渠道智能推送。
★ 60kMirrorWe. Model WeChat friends and let AI agents chat, post & grow relationships on their own
★ 5RL. Scalable toolkit for efficient model reinforcement
★ 1Step-Audio-R1. Python
★ 684tilelang-paddle. Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels
★ 4ax-llm. Explore LLM model deployment based on AXera's AI chips
★ 160ncnn_llm. A repo for llm on ncnn
★ 11flash-moba. C++
★ 249996.ICU. Repo for counting stars and contributing. Press F to pay respect to glorious developers.
★ 276kFlowise. Build AI Agents, Visually
★ 55kDeepSpeedExamples. Example models using DeepSpeed
★ 6.8kKimi-K2. Kimi K2 is the large language model series developed by Moonshot AI team
★ 11kPaddleOCR-ncnn-CPP. C++ implementations of PP-OCRv3/4/5/6 using ncnn for inference.
★ 91LLaVA. [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
★ 25kpiano_transcription. Python
★ 2kPlateRecognition_ncnn. 高性能 高精度 大陆车牌、港澳车牌、台湾车牌 韩国车牌(South Korea LPR)识别 代码开源(ncnn移植)
★ 46mllm_pretrain_tutorial. HTML
★ 2TinyTorch. A lightweight deep learning training framework implemented from scratch in C++, featuring a PyTorch-style API.
★ 193Kimi-Linear.
★ 1.4kAI-Trader. "AI-Trader: 100% Fully-Automated Agent-Native Trading"
★ 21ktinker. Training API and CLI
★ 538kosong. The LLM abstraction layer for modern AI agent applications.
★ 515kimi-cli. Kimi Code CLI is your next CLI agent.
★ 9.1kGenos. A Genomic Foundation Model
★ 166dexbotic-benchmark. Python
★ 30dexbotic. Dexbotic: Open-Source Vision-Language-Action Toolbox
★ 1.2krtp-llm. RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.
★ 1.3kDeepSeek-OCR. Contexts Optical Compression
★ 24kconvnetjs. Deep Learning in Javascript. Train Convolutional Neural Networks (or ordinary ones) in your browser.
★ 11kncnn-benchmark. Using ncnn to test the reasoning performance of neural network
★ 37ncnn-android-whisper. Python
★ 21ROGRAG. [ACL2025 demo track] ROGRAG: A Robustly Optimized GraphRAG Framework
★ 1nanochat. The best ChatGPT that $100 can buy.
★ 56kpyaxcl. Python
★ 11moonshot-provider. 🍒 Cherry Studio is a desktop client that supports for multiple LLM providers.
★ 1K2-Vendor-Verifier. Verify Precision of all Kimi K2 API Vendor
★ 578aimet. AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.
★ 2.7kredalert2. 红色警戒2源代码 Red Alert2 Source Code
★ 864Qwen3-Omni. Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, images, and video, as well as generating speech in real time.
★ 3.9kDeepSeek-V3.2-Exp. Python
★ 1.6kDeepGEMM. DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
★ 31swipl-devel. SWI-Prolog Main development repository
★ 1.3kSQLBot. 🔥 基于大模型和 RAG 的智能问数系统,对话式数据分析神器。Text-to-SQL Generation via LLMs using RAG.
★ 6.4kflash-kmeans. Fast and memory-efficient exact kmeans
★ 701pieces. Pieces of code to archive
★ 1LLaVA-OneVision-2. Fully Open Framework for Democratized Multimodal Training
★ 1.1kigraph. Library for the analysis of networks
★ 2kblislab. BLISlab: A Sandbox for Optimizing GEMM
★ 568DeepResearch. Tongyi Deep Research, the Leading Open-source Deep Research Agent
★ 20kAwesome-Scientific-Datasets-and-LLMs. A curated collection of papers, datasets, and resources on Scientific Datasets and Large Language Models (LLMs)
★ 457ncnn_mp. Lightweight ncnn C API bindings for MicroPython
★ 13CUDA_gemm. A simple high performance CUDA GEMM implementation.
★ 436godot. Godot Engine – Multi-platform 2D and 3D game engine
★ 114k