deepseek-ai

Mirrored from GitHub organization: deepseek-ai

A lightweight library for xPU kernel JIT compilation
Updated 2026-11-03 16:16:04 +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
FlashMLA: Efficient Multi-head Latent Attention Kernels
Updated 2026-10-27 02:50:39 +00:00
DeepGEMM-Ascend: clean and efficient matrix multiplication kernel library for Huawei Ascend NPUs
Updated 2026-10-14 09:22:30 +00:00
An internal component used by DeepSeek Harness
Updated 2026-10-08 12:32:57 +00:00
Clangd for Ascend for Code Lint & Code Completion
Updated 2026-09-29 10:22:10 +00:00
A high-performance distributed file system designed to address the challenges of AI training and inference workloads.
Updated 2026-05-07 09:31:53 +00:00