Repository navigation

deepseek-v3

Website
Wikipedia

SGLang is a fast serving framework for large language models and vision language models.

CUDA inference llama llava 大语言模型 llm-serving moe PyTorch transformer vlm llama3 deepseek deepseek-v3 deepseek-r1 qwen3 llama4 blackwell llama5 openai kimi

Python

17029

2670

2 小时前

xlite-dev / Awesome-LLM-Inference

📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉

flash-attention tensorrt-llm vllm llm-inference deepseek deepseek-v3 deepseek-r1 qwen3

Python

4406

300

1 天前

LLM-Red-Team / deepseek-free-api

🚀 DeepSeek-V3 & R1大模型逆向API【特长：良心厂商】（官方贼便宜，建议直接走官方），支持高速流式输出、多轮对话，联网搜索，R1深度思考，零配置部署，多路token支持，仅供测试，如需商用请前往官方开放平台。

chat-api 聊天机器人 ChatGPT API deepseek 大语言模型 deepseek-r1 deepseek-v3 deepseek-api

TypeScript

2670

771

3 个月前

AIDC-AI / ComfyUI-Copilot

An AI-powered custom node for ComfyUI designed to enhance workflow automation and provide intelligent assistance

agent 人工智能 comfy-ui copilot deepseek deepseek-v3 gpt-4 llm-agent rag flux stable-diffusion comfyui comfyui-nodes

TypeScript

2456

177

4 小时前

Xxiii8322766509 / NagaAgent

娜迦本地智能体，基于多智能体与多MCP兼容架构的通用型 AI 助手

agentic-ai agents deepseek-v3 mcp-client openai mcp toolcall

Python

745

9 小时前

ModelTC / LightCompress

[EMNLP 2024 Industry Track] This is the official PyTorch implementation of "LLMC: Benchmarking Large Language Model Quantization with a Versatile Compression Toolkit".

部署大语言模型 pruning quantization 工具 benchmark evaluation large-language-models internlm2 smoothquant post-training-quantization mixtral vllm deepseek-r1 deepseek-v3

Python

544

7 天前

Gen-Verse / ReasonFlux

ReasonFlux Series - A family of LLM post-training algorithms focusing on data selection, reinforcement learning, and inference scaling

chain-of-thought deepseek-r1 reinforcement-learning deepseek-v3

Python

481

15 天前

zjunlp / OmniThink

OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinking

人工智能 generation gpt information-seeking knowledge-augmented-generation large-language-models 自然语言处理 qwen retrieval-augmented-generation report-generation deepseek-r1 deepseek-v3 gpt4o qwen2-5

Python

456

4 个月前

deepseek-php / deepseek-php-client

⚡️ A robust and developer-friendly, and community-driven PHP Client that provides a clean, extensible interface for integrating with the DeepSeek AI API.

deepseek deepseek-api deepseek-r1 deepseek-v3 人工智能 API 自然语言处理 text-generation

PHP

434

1 个月前

meysamhadeli / codai

Codai is an AI code assistant that helps developers through a session-based CLI, providing intelligent code suggestions, refactoring, and code reviews based on the full context of the project.