qwen_megakernel
Aggressive decode optimizations for Qwen3-0.6B on RTX 5090
File Explorer
Download Latest Version (.zip)- megakernel-1.png
- kernel.cu
- torch_bindings.cpp
- __init__.py
- bench.py
- build.py
- model.py
- .gitignore
- LICENSE
- README.md
- requirements.txt
# Installation Guide
1. Get the code
git clone https://github.com/AlpinDale/qwen_megakernel
Downloads the entire project code from GitHub to your computer.
cd qwen_megakernel
Moves into the project folder you just downloaded.
2. Python
Easy RecommendedPrerequisites
uv pip install -r requirements.txt
Installs the Python libraries listed in requirements.txt (or similar).
python -m qwen_megakernel.bench
Runs the Python script (or module).
If it runs without errors and prints output in the terminal, it worked.
Pulled directly from this repo's README.
// repository documentation
Was this content helpful?
(0 ratings)
