Alternatives and similar repositories for DeepLearningSystem

Users that are interested in DeepLearningSystem are comparing it to the libraries listed below

• jd-opensource / xllm
  A high-performance inference engine for LLMs, optimized for diverse AI accelerators.
  ☆934Updated this week
• smart-lty / nano-PEARL
  Draft-Target Disaggregation LLM Serving System via Parallel Speculative Decoding.
  ☆149Updated last month
• antgroup / Research-Venus
  Deep Research
  ☆303Updated 5 months ago
• KylinC / ChatFinance
  金融财报问答大模型LLM
  ☆218Updated last year
• FreedomIntelligence / RAG-Instruct
  [EMNLP 2025] RAG-Instruct: Boosting LLMs with Diverse Retrieval-Augmented Instructions
  ☆137Updated 9 months ago
• zkkli / RepQ-ViT
  [ICCV 2023] RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformers
  ☆140Updated 2 years ago
• SoraFlows / GoOut.tools
  Go Out出海第一步，搞定工具库 独立开发者出海技术栈和工具, 收集的一些有用的出海工具和资源，可以帮助你更好地了解和进入海外市场。 挑选标准 帮助独立开发者提升开发效率 帮助独立开发者降低成本 市场上足够流行
  ☆22Updated last year
• RockChinQ / awesome-dify-integration
  Collection of projects / apps integrated with dify service API.
  ☆19Updated last year
• Tlntin / Qwen-TensorRT-LLM
  ☆624Updated last year
• footuser / yolo_wechat_qrcode
  提高微信二维码识别精确率的小工具
  ☆101Updated 9 months ago
• mire403 / VisionForge
  VisionForge是一个轻量级、高扩展性的大模型图片训练&描述工具生成器，支持多家大模型API（Google、OpenAI 兼容、DeepSeek、Qwen、GLM、Claude、Doubao、自定义模型）。 它提供多图片上传、提示词优化、自动生成JSONL训练数据、多…
  ☆45Updated this week
• codefuse-ai / ModelCache
  A LLM semantic caching system aiming to enhance user experience by reducing response time via cached query-result pairs.
  ☆955Updated 6 months ago
• OpenGithubs / selectedColumn
  Github开源项目精选栏目,不定期更新
  ☆236Updated 2 years ago
• cr7258 / ai-infra-learning
  This repository organizes materials, recordings, and schedules related to AI-infra learning meetings.
  ☆303Updated 3 weeks ago
• linyueqian / VERA
  ☆117Updated 2 months ago
• caozhanhao / wxserver
  C++企业微信消息推送服务器
  ☆37Updated 2 years ago
• flash-algo / flash-sparse-attention
  Trainable fast and memory-efficient sparse attention
  ☆516Updated last week
• antgroup / HumanSense
  ☆26Updated 2 months ago
• zkkli / I-ViT
  [ICCV 2023] I-ViT: Integer-only Quantization for Efficient Vision Transformer Inference
  ☆200Updated last year
• meituan-longcat / UNO-Bench
  Omni Model Benchmark with high quality and diversity, which reveals the Compositional Law. We’re now focused on Chinese scenarios — and a…
  ☆74Updated 2 weeks ago
• julxxy / xxl-job-r3
  A third-party React-based web back-end service for XXL-JOB-PANEL-R3.
  ☆99Updated 5 months ago
• LWL-cpu / Question-Free-Fine-Tuning
  [NeurIPS 2025 spotlight] QFFT, Question-Free Fine-Tuning for Adaptive Reasoning
  ☆91Updated 2 months ago
• PRIS-CV / FairHuman
  ☆70Updated 6 months ago
• kexinoh / free-OKC
  OK Computer in a Box: Your Self-Hosted Agent Workflow Layer
  ☆130Updated 3 weeks ago
• Zhang-hs-home / RPC
  A single RPC framework based on Go
  ☆19Updated 2 years ago
• meituan-longcat / LongCat-Flash-Thinking-2601
  ☆185Updated this week
• myhhub / cmake-project
  CMake完整使用教程。CMake教程包括一系列循序渐进的任务，介绍CMake信息，展示如何实现目标。
  ☆276Updated 4 years ago
• go-lynx / lynx
  The Plug-and-Play Go Microservices Framework, Unleash the Power of Simplicity: With the Plug-and-Play Go Microservices Framework, we tran…
  ☆122Updated last week
• Tongjilibo / rec4torch
  推荐系统的pytorch算法实现
  ☆76Updated last year
• Tongjilibo / torch4keras
  bert4torch底层训练框架，用keras风格写torch代码
  ☆78Updated last week