DeepSeek V4 Flash on a Single AMD MI300X(github.com)

366 points by zhoutong 2 months ago | 88 comments

GitHub repository with patches, tuning files, and config for running DeepSeek V4 Flash on a single AMD MI300X GPU.

DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling(github.com)

381 points by mfiguiere 1 year ago | 65 comments

GitHub repository for DeepSeek's DeepGEMM, a library of clean and efficient FP8 GEMM kernels with fine-grained scaling, released under the MIT license.

DualPipe: Bidirectional pipeline parallelism algorithm(github.com)

165 points by mfiguiere 1 year ago | 19 comments

DeepSeek-v3.2-Exp(github.com)

271 points by meetpateltech 1 year ago | 41 comments

LPLB: An early research stage MoE load balancer based on linear programming(github.com)

27 points by simonpure 11 months ago | 0 comments

DeepSeek open source DeepEP – library for MoE training and Inference(github.com)

473 points by helloericsf 1 year ago | 66 comments

GitHub repository for DeepEP, DeepSeek's open-source expert-parallel communication library for Mixture-of-Experts model training and inference.

DeepSeek open source DeepEP – library for MoE training and Inference(github.com)

473 points by helloericsf 1 year ago | 66 comments

GitHub repository for DeepEP, DeepSeek's open-source expert-parallel communication library for Mixture-of-Experts model training and inference.

DeepSeek OCR(github.com)

939 points by pierre 1 year ago | 226 comments

GitHub repository for DeepSeek-OCR, DeepSeek's open-source "Contexts Optical Compression" OCR model, with code, paper PDF, and MIT license.

DeepSeek-R1(github.com)

1582 points by meetpateltech 1 year ago | 585 comments

GitHub repository for DeepSeek-R1, DeepSeek's open reasoning language model, with the paper PDF, figures, README, and MIT license.

DeepSeek: DeepSeek v4.1 Flash 1017(openrouter.ai)

499 points by theanonymousone 9 days ago | 264 comments

OpenRouter model page for DeepSeek V4.1 Flash 1017, a sparse mixture-of-experts LLM snapshot with pricing, 1M context, and API access details.

DeepSeek reasonix, DeepSeek native coding agent with high caching and low cost(esengine.github.io)

706 points by Alifatisk 5 months ago | 273 comments

Project homepage for Reasonix, an open-source DeepSeek-native terminal coding agent built around DeepSeek's prefix cache for low-cost long sessions.

DeepSeek-Prover-V2(github.com)

359 points by meetpateltech 1 year ago | 74 comments

GitHub repository for DeepSeek-Prover-V2, DeepSeek's model for formal theorem proving, containing a paper PDF, README, model license, and miniF2F solutions.