NVIDIA-NeMo/Automodel
🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support
Topic: deepseek-v4-flash
40 repositories
notatestuser/ds4-control
macOS menubar app for fast local DeepSeek V4.1, with 1M context.
deepseek-php/deepseek-php-client
⚡️ A community driven PHP client for DeepSeek AI, designed to bring clean API access, fluent developer experience, and framework-friendly integration to PHP applications.
yxlao/deepseek-cursor-proxy
Fixes missing reasoning_content for DeepSeek V4
Entrpi/ds4-on-spark
Entrpi/ds4, a Blackwell CUDA perf fork of antirez/ds4 on NVIDIA DGX Spark: one-command install, ~3x upstream prefill, ~1.5x decode, DSpark, and full continuous batch support
snake-aabb-wtf/deepseek-web2api-free
基于 FastAPI 的 DeepSeek Chat 反向代理，将 DeepSeek 网页版的 API 转换为 OpenAI 兼容格式。 支持流式/非流式对话、专家模式、深度思考（reasoning_content）、工具调用（DSML prompt injection）。 自动处理 PoW 鉴权挑战，无需官方 API Key。
yanun0323/Whallm
DeepSeek-V4-Flash-0731 284B inference in ~25 GB of RAM / Qwen3.8-Next-Flash-FP8 inference in ~18 GB of RAM on any M-series MacBook
baker27727/ds4-8gb-cpu
DeepSeek V4 Flash CPU/NVMe research fork: 78.62 GiB GGUF validated on 7.7 GiB RAM, CPU-only, using demand paging.
local-ai-zone/local-ai-zone.github.io
My public AI learning journey — sharing what I learn, build, test, and discover across AI. Traffic: 7K+ monthly clicks · 150K+ AI citations/month · 5.5 average search position across search engines. local-ai-zone.github.io
hmziqrs/claude-multi
A tool to have multiple claude-code instance with deepseek, minimax, and z.ai glm models
pepuscz/strix-halo-deepseek-v4-flash
Production-ready, reproducible Ansible for DeepSeek V4 Flash on 128 GiB AMD Strix Halo, with two qualified Vulkan/ROCmFPX stacks, matched quality and throughput benchmarks, and 512K context validation.
flaqai/deepeseek-harness-guide
Guide for development with DeepSeek Harness. Building plugin for DeepSeek Harness Project.
Reederey87/dgx-spark-2x-deepseek-v4-flash
Reproducible kit to deploy DeepSeek-V4-Flash-DSpark on a 2× NVIDIA DGX Spark (GB10) cluster: vLLM TP=2 over QSFP 200GbE, NVFP4 KV, DSpark speculative decoding, 1M context, systemd self-heal. Apache-2.0.
QubridAI-Inc/qubrid-cookbook
A collection of recipes/notebooks showcasing use-cases of open-source models with Qubrid AI.
yuyukosama2004/codex-deepseek-max-guide
Codex 桌面版为 DeepSeek-V4-Flash 开启 Max 推理档位的完整排障与配置指南 / Complete guide to enable Max reasoning effort for DeepSeek-V4-Flash in Codex desktop
SIMON-WORLD/codex-deepseek-vision
Codex vision bridge for DeepSeek V4 Flash: give text-only DeepSeek image capability in Codex. Local proxy turns pasted images and view_image into text via free GLM-4V-Flash or any OpenAI-compatible vision API. No GPU, no Ollama.
Akgithub2028/LOOM
Dynamic Agent-to-Agent (A2A) task graph generation, subtask independence verification, and parallel multi-agent orchestration
mrbeandev/deepseek-browser-agent
Supercharge your daily workflows! Autonomously browse pages, scrape content, switch tabs, fill out inputs, and stream Chain-of-Thought (CoT) reasoning under granular human-in-the-loop safety switches and glassmorphic UI controls.
mvmv1428/deepcode-v4
Unlock Claude Code with DeepSeek V4. Get Anthropic's agent tools with 95% lower costs and local vision.
NimbleMarkets/ds4go
Golang wrapper for DwarfStar4 (ds4)
dyrnq/ai-adapter
A Rust proxy that exposes an **OpenAI Responses API** interface, translating to various upstream backends (DeepSeek, OpenAI, Anthropic) with full streaming SSE support. Built for Codex CLI and similar tools hardcoded to OpenAI.
GavinCnod/deepseek-api-usage-analysis
A browser-side analytics dashboard for DeepSeek API usage. Drag your monthly CSV exports onto the page and get instant cost charts, per-key breakdowns, cache analysis, and usage trends — all processed locally in your browser. no upload, no signup. 一款纯浏览器端的 DeepSeek API 用量分析仪表盘。将月度 CSV 导出文件拖拽到页面，即刻获取费用图表、各 Key 用量明细、缓存分析和用量趋势 — 所有数据均在浏览器本地处理。
54cndr/DS-Code
AI编程助手 | AI coding agent
aispin-dev/llm-as-a-Verifier-dsh
LLM-as-a-Verifier (arXiv:2607.05391) as a dsh plugin — Best-of-N conversation mode: give DeepSeek V4 Flash test-time scaling. Bo5 self-verification hits 88% on Terminal-Bench 2.1, beating some frontier models at a fraction of the cost. Fine-grained logprob-expectation scoring, PPT tournament, zero-config.
wwwAngHua/dsh-liquid-glass
DeepSeek Harness 超高自由度的个性化插件，支持液态玻璃效果、自定义图片、视频背景、字体颜色，同时支持批准提示音和账户余额查询。
theJian/squint-mcp
Most LLMs see images. With squint-mcp, the rest imagine seeing them.
null5069/dsh-better-stats
DSH Web composer stats strip: official CNY pricing with auto-synced peak/off-peak tiers, per-model accounting, live LLM/tool timers, agent-team tree merge, DeepSeek balance, budget alerts, streaming cost estimates
daimonionnn/multi-gpu-llm-toolkit
Run llama.cpp across two GPUs of different vendors at once (AMD ROCm/HIP or Vulkan + NVIDIA CUDA) in one llama-server process, no RPC server. Windows (PowerShell) and Linux (bash) implementations, shared docs on ROCm memory bugs and benchmarks.
guang384/deepseek-v4-flash-onlycpu
DeepSeek-V4-Flash 推理引擎 — 纯 Rust / 纯 CPU / 零依赖 / MoE 284B 满血模型本地推理
leemjnnkdzuy/shallow-seek
A high-performance API Gateway that standardizes DeepSeek endpoints for AI agents and developer tools (fully compatible with OpenAI, Claude, and Gemini protocols).