-
@tsinghua-ideal, Tsinghua University; @deepseek-ai
- Beijing, China
- https://chaofanlin.com/
- @siriusneox
- https://m.etric.space/
Lists (5)
Sort Name ascending (A-Z)
Stars
Training Reasoning Models in Simulation to Natively Use Real Robots
Open ML Compiler Foundation for the Agentic Era
DeepInfer: High-performance, large-scale inference framework for DeepSeek models
Perplexity open source garden for inference technology
Minimal agent harness in one Bash file. One-line quick start. Bootloader agent for bare-metal servers.
A high-performance communication library for machine learning training and inference on Huawei Ascend NPUs.
DeepGEMM-Ascend: clean and efficient matrix multiplication kernel library for Huawei Ascend NPUs
An Open Compiler Harness for Agentic GPU Programming
A lightweight library for xPU kernel JIT compilation
DeepSelect: TopK kernels for DeepSeek Sparse Attention (DSA) and Samplers
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
FreeToken brings datacenter-scale model serving to your desktop. Run massive models locally, fast and efficiently.
A Programming Paradigm for Spatiotemporal Composability
DeepSeek Harness: Everything is a Plugin.
A tutorial on modern GPU programming for machine learning systems
Reference implementation and examples of the CuTe Layout representation and algebra.
MoonEP: A Perfectly Balanced Expert Parallelism Library via Dynamic Redundant Experts
A reliable coding agent for complex software engineering tasks.