deepseek-v3 repositories

Trending repositories tagged deepseek-v3, ranked by trending score. Updated daily.

  1. 1
    vllm-project/vllm

    A high-throughput and memory-efficient inference and serving engine for LLMs

    GitHub · Python · 97,265 stars · 25,080 forks · +109 stars in 24 hours · Trending score 4.26

  2. 2
    atharvotech/FreeDeepseekAPI-EN

    Local OpenAI-compatible API proxy for DeepSeek Web Chat (Global English Version). Connects DeepSeek to Open WebUI, Claude Code, and OpenAI SDK tools. Maintained by Atharvotech.

    GitHub · JavaScript · 97 stars · 12 forks · +54 stars in 24 hours · Trending score 2.96

  3. 3
    batchgen-project/batchgen

    High-Throughput Batch Inference

    GitHub · C++ · 22 stars · 1 forks · 0 stars in 24 hours · Trending score 0.32

  4. 4
    Liao-Ke/everyday

    ✨ 让经典名言焕发新生!基于LLM模型动态生成创意故事,用AI重新诠释金山每日一句的智慧结晶

    GitHub · Markdown · 70 stars · 11 forks · 0 stars in 24 hours · Trending score 0.09

  5. 5
    YeonwooSung/llm-architecture-from-scratch

    Implementing LLM architectures from scratch in PyTorch

    GitHub · Python · 856 stars · 4 forks · 0 stars in 24 hours · Trending score 0.09

  6. 6
    InternLM/xtuner

    A Next-Generation Training Engine Built for Ultra-Large MoE Models

    GitHub · Python · 5,223 stars · 468 forks · 0 stars in 24 hours · Trending score 0.04

  7. 7
    lidaoyang/dot-chat

    这是一个基于Web技术开发的高仿微信聊天软件,支持手机端和PC端。用户可以通过浏览器访问,实现即时通讯、消息推送、语音视频通话等功能。已接入 DeepSeek-V3 AI智能回复功能,如果不知道怎么回复,可以使用"AI智能回复"来帮你回复。

    GitHub · Java · 32 stars · 8 forks · 0 stars in 24 hours · Trending score 0.00

  8. 8
    DeepSeekV4Flash0731/DeepSeek-V4-Flash-0731

    DeepSeek V4 Flash 0731 - free deepseek v4 flash download, gguf, ollama, deepseek v4 pro 0813. deepseek v4 flash vs pro, benchmark, MoE, 1M context, compressed sparse attention, coding. CUDA/CPU, no API key, Windows local AI. Download:🡇

    GitHub · C++ · 27 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00

  9. 9
    Drobiazkin/agent-gpu-calculator

    Single-file GPU/RAM sizing calculator for LLM agent sessions on vLLM: KV-cache offload to RAM, prefix caching, MLA/DSA and hybrid models, TP chosen per model × GPU pair (H100–B300). Runs in the browser, no dependencies.

    GitHub · HTML · 8 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00

  10. 10
    mistaken-contadino194/ComfyUI-MiniMax-H3-Turbo

    Run MiniMax-H3 video plus synchronized audio in 4 sampling steps using the Turbo LoRA, with drop-in nodes for ComfyUI workflows.

    GitHub · Python · 5 stars · 1 forks · 0 stars in 24 hours · Trending score 0.00