DeepGEMM
DeepGEMM: clean and efficient BLAS kernel library on GPU
About this project
DeepGEMM DeepGEMM is a unified, high-performance tensor core kernel library that brings together the key computation primitives of modern large language models — GEMMs (FP8, FP4, BF16), fused MoE with overlapped communication (Mega MoE), MQA scoring for the lightning indexer, HyperConnection (HC), and more — into a single, cohesive CUDA codebase. All kernels are compiled at runtime via a lightweight Just-In-Time (JIT) module, requiring no CUDA compilation during installation. DeepGEMM leverages some concepts from CUTLASS and CuTe, but avoids heavy reliance on their templates or algebras. The library is designed for simplicity, with only a limited number of core kernel functions, making it…
Technologies
Project health
GitHub
Reviews
Built by
Maintain deepseek-ai/DeepGEMM? Claiming verifies admin access through your GitHub account and gives you control of this listing.
