14 projects
deepinfer-flashmla
FlashMLA: Efficient MLA kernel for Hopper and Ascend GPUs
deepinfer-ep
DeepEP: High-Performance Expert Parallelism Communication Library
deepinfer-gemm
DeepGEMM: Clean and efficient FP8 GEMM kernels with fine-grained scaling
deepinfer
DeepInfer: High-performance, large-scale inference framework for DeepSeek models
mortgagekit
Mortgage math and modeling utilities used by the book
xuanxin
Markdown blog to beautiful static HTML — write .md, customize CSS, publish.
x2harness
XuanXin Harness: Production-grade Reference Architecture for Autonomous Coding Agents
coding-agents
The reference software engineering harness and runtime for autonomous coding agents.
peanutbook
Book Building Utilities - Convert markdown chapters to PDF and build complete books
mathicon
Mathematics for AI Utilities
math4ai
Mathematics for AI Utilities
bubble-book
Book Building Utilities - Convert markdown chapters to PDF and build complete books
distai
Distributed PyTorch helpers for process setup, sync printing, and model utilities
deepseek
Deepseek API Library
