deepseek-ai

Mirrored from GitHub organization: deepseek-ai

Contexts Optical Compression
Updated 2026-11-05 06:44:57 +00:00
DeepSeek Harness: Everything is a Plugin.
Updated 2026-11-04 08:40:00 +00:00
A lightweight library for xPU kernel JIT compilation
Updated 2026-11-03 16:16:04 +00:00
DeepInfer: High-performance, large-scale inference framework for DeepSeek models
Updated 2026-11-03 07:31:40 +00:00
A high-performance communication library for machine learning training and inference on Huawei Ascend NPUs.
Updated 2026-11-03 01:45:18 +00:00
Towards a More Autonomous Agent System
Updated 2026-10-31 12:06:31 +00:00
FlashMLA: Efficient Multi-head Latent Attention Kernels
Updated 2026-10-27 02:50:39 +00:00
DeepEP: an efficient expert-parallel communication library
Updated 2026-10-21 03:50:43 +00:00
DeepGEMM: clean and efficient BLAS kernel library on GPU
Updated 2026-10-20 05:07:07 +00:00
Updated 2026-10-19 17:51:02 +00:00
DeepGEMM-Ascend: clean and efficient matrix multiplication kernel library for Huawei Ascend NPUs
Updated 2026-10-14 09:22:30 +00:00
A kernel library written in tilelang
Updated 2026-10-14 05:49:06 +00:00
An internal component used by DeepSeek Harness
Updated 2026-10-08 12:32:57 +00:00
DeepSelect: TopK kernels for DeepSeek Sparse Attention (DSA) and Samplers
Updated 2026-09-30 01:54:53 +00:00
An internal component used by DeepSeek Harness
Updated 2026-09-29 17:42:53 +00:00