🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support
macOS menubar app for fast local DeepSeek V4.1, with 1M context.
⚡️ A community driven PHP client for DeepSeek AI, designed to bring clean API access, fluent developer experience, and framework-friendly integration to PHP applications.
Fixes missing reasoning_content for DeepSeek V4
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。
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
DeepSeek V4 Flash CPU/NVMe research fork: 78.62 GiB GGUF validated on 7.7 GiB RAM, CPU-only, using demand paging.
deepseek v 4.1 flash, Kimi K3, deepseek v4 flash, glm 5.2, qwen 3.8 27b, Muse Glimmer, Nemotron, glm 5.3, ox alpha, glm 5.3 flash, mimo 3
A tool to have multiple claude-code instance with deepseek, minimax, and z.ai glm models
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.
DeepSeek 逆向 API 支持 Deepseek V4
Guide for development with DeepSeek Harness. Building plugin for DeepSeek Harness Project.
deepseek-v4-flash API (deepseekv4flash / deepseek v4 flash): input $0.3429; cached_input $0.0686; output $1.0286. Model id, llm settings, curl and Python examples over an OpenAI-co
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.
AI API 中转站/网关中文文档 · deepseek-v4-flash / deepseekv4flash API：input $0.3429; cached_input $0.0686; output $1.0286。模型 ID、参数、curl 与 Python 示例，OpenAI 兼容接口，$1 起充。
A collection of recipes/notebooks showcasing use-cases of open-source models with Qubrid AI.
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
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.
Dynamic Agent-to-Agent (A2A) task graph generation, subtask independence verification, and parallel multi-agent orchestration
To associate your repository with the deepseek-v4-flash topic, visit your repo's landing page and select "manage topics."