GeezerVison is showing github.com โ yeahdongcn - Overview
- โก AI Inference/Infrastructure SDE at MooreThreads โ building AI inference systems and GPU clusters.
- ๐ค Contributing MUSA GPU support to open-source AI frameworks:

- ๐ Maintaining MUSA inference applications and compatibility libraries:

- ๐ง Building developer tools for AI and cloud-native workflows:

- ๐ฌ Building Nautilus Studio โ an agentic AI film workshop built around Qwen-Image-Edit-2511 and MiniMax-H3, turning a creative brief into an editable storyboard, continuous video clips, and a long-form cut.
- ๐ Building Apple ecosystem tools and libraries:

- ๐ Building NIGHT CITY โ Pixel Edition with AI (PLAY!): night-city-pixel
- ๐๏ธ Previously at VMware and Sangfor, focused on cloud-native and virtualization technologies.
- ๐ฌ Reach me at [email protected] | LinkedIn
Pinned
Loading
-
SGLang is a high-performance serving framework for large language models and multimodal models.
Python
38.8k
10.4k
-
An adapter layer that ensures torch_musa๐ฆ delivers a CUDA-compatible PyTorch experience.
Python
45
20
-
Forked from vllm-project/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
Python
131
12
-
Forked from ollama/ollama
Get up and running with OpenAI gpt-oss, DeepSeek-R1, Gemma 3 and other models on MTGPU.
Go
37
3
-
Convenience methods for creating color using RGBA hex string.
Swift
1.2k
141
-
1D and 2D barcodes reader and generators for iOS 8 with delightful controls. Now Swift.
Swift
720
182
Uh oh!
There was an error while loading. Please reload this page.