$ account deepseek-ai
This repository is a curated, community-maintained 'awesome list' cataloging third-party software, plugins, frameworks, and tools that integrate with DeepSeek's API and models. It contains no application source code, data pipelines, or executable components. The repository's sole purpose is documentation and discovery: it provides a categorized index (applications, AI agent frameworks, RAG frameworks, IDE plugins, browser extensions, etc.) with links, logos, and brief descriptions. Each integration is documented in the docs/ directory with setup instructions, configuration snippets, and multilingual translations. While not a software system itself, it serves as a vital reference for developers building on DeepSeek, and the consistent per-integration documentation template is a reusable pattern for similar curations. The repository is actively maintained with frequent contributions and translations, though the value depends entirely on the listed projects remaining current and accessible.
DeepSeek-OCR is an inference repository for a multimodal OCR model that combines vision encoders (SAM and CLIP) with a large language model (DeepSeek-V2/V3) to perform optical character recognition with layout awareness, supporting native and dynamic resolution processing. The system provides two inference paths: a Hugging Face Transformers integration for simple usage and a custom vLLM integration for high-throughput batched inference, including PDF processing and evaluation benchmarks. The architecture is a monolithic model definition with separate modules for vision encoding (deepencoder), image preprocessing (process), and vLLM glue code, all tightly coupled to the specific model architecture. The codebase is functional and demonstrates competent engineering for research-grade inference, but lacks production hardening, documentation, and consistent coding standards.
DeepEP is a high-performance communication library developed by DeepSeek for distributed Mixture-of-Experts (MoE) model training and inference. Its primary function is implementing expert-parallel (EP) all-to-all dispatch and combine operations, routing tokens to the correct GPU holding an expert and gathering the results. It also provides general collective communication primitives (all-reduce, reduce-scatter, all-gather) optimized for multi-node multi-GPU clusters with NVLink and RDMA interconnects. The architecture is a hybrid Python/C++/CUDA library. The Python layer (deep_ep) provides user-facing buffer classes (EPBuffer, BucketBuffer, EngramBuffer, PPBuffer) and orchestration utilities. The C++/CUDA layer (csrc/, deep_ep/include/) contains JIT-compiled kernels that leverage cutting-edge NVIDIA Hopper/Blackwell features (TMA, mbarriers, NCCL GIN) for maximum performance. The library is designed to overlap communication with computation through deferred epilogue patterns. The codebase exhibits exceptional craftsmanship in its low-level CUDA kernels, particularly the ptx.cuh utility layer and the distributed barrier implementations. The Python utilities (EventOverlap, weak_lru, EnvOverride, BufferAllocator) are well-isolated, elegant patterns that are genuinely reusable in other GPU or distributed computing projects. However, the library has a high technical drift risk due to its deep reliance on experimental and rapidly evolving NVIDIA APIs (NCCL device-side, specific CUDA architecture features). It is tightly coupled to a specific hardware stack (Hopper+ GPUs, NVLink, RDMA) and software versions (CUDA 13.1+, NCCL 2.32.3+). While actively maintained, its specialized nature and complex build system limit its applicability outside of large-scale MoE training on cutting-edge NVIDIA clusters.
This repository is a research codebase for training and evaluating draft models for speculative decoding, supporting three algorithms: DSpark, DFlash, and Eagle3. It provides a full pipeline from data preparation (downloading prompts, regenerating answers with a target model via SGLang, and precomputing a large binary cache of target hidden states) to distributed training with FSDP and BF16, and evaluation on standard LLM benchmarks (GSM8K, MATH500, AIME, HumanEval, etc.). The code is well-structured with reusable components for configuration, distributed utilities, checkpointing, metrics, and custom attention masks. While primarily a research artifact, it exhibits strong engineering practices and several modules that could be extracted for other large-scale ML projects. The repository is hybrid in nature: it contains both application-like training/evaluation scripts and data_research elements such as data pipelines and evaluation datasets.
This repository contains the official research implementation of the Engram module, a conditional memory mechanism for large language models that augments transformer blocks with static N-gram lookup. The codebase is a single standalone Python demo script (`engram_demo_v1.py`) that illustrates the core data flow: tokenization, compression, hash-based N-gram indexing, multi-head embedding retrieval, gating via learned keys and query dot-product, and a short depthwise convolution with per-group RMSNorm. The architecture is a mock LLM (embedding, transformer blocks with mocked Attention/MoE, linear head) to focus solely on the Engram module. The repo is a research artifact, not a production service; it lacks tests, packaging, and error handling but provides a clear, commented implementation of the novel hash-based conditional memory pattern. The primary value for engineers is the extractable pattern for deterministic N-gram lookup and gating, and the depthwise convolution with group normalization.