Published February 28, 2025
| Version v1.0
Software
Open
SpInfer-artifact
Authors/Creators
-
1.
Guangzhou HKUST Fok Ying Tung Research Institute
Description
Artifact of EuroSys 2025 paper SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs. See our github repo for instructions on how to install and run the artifact.
Files
SpInfer-ae-codes.zip
Files
(151.9 kB)
| Name | Size | Download all |
|---|---|---|
|
md5:d41008d805de3884d9e46957b00d2f3d
|
151.9 kB | Preview Download |
Additional details
Software
- Repository URL
- https://github.com/HPMLL/SpInfer_EuroSys25
- Programming language
- C++ , Cuda , Python
- Development Status
- Active