代码库
DeepInfer: High-performance, large-scale inference framework for DeepSeek models
Python
An internal component used by DeepSeek Harness
JavaScript
deepseekdeepseek-harness
DeepGEMM-Ascend: clean and efficient matrix multiplication kernel library for Huawei Ascend NPUs
C++
Rust
A lightweight library for xPU kernel JIT compilation
C++
Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models
Python
FlashMLA: Efficient Multi-head Latent Attention Kernels
C++
DeepSeek Harness: Everything is a Plugin.
TypeScript
ai-agentscordisdshdsh-plugin
DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms
Python
Python
DeepSeek Coder: Let the Code Write Itself
Python
DeepEP: an efficient expert-parallel communication library
Cuda
DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence
A kernel library written in tilelang
Python
DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models
Python
DeepGEMM: clean and efficient BLAS kernel library on GPU
Cuda
Contexts Optical Compression
Python
A high-performance distributed file system designed to address the challenges of AI training and inference workloads.
C++
distributed-file-system
DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
Python