neural-nova
/

Qwen3-4B-Instruct-2507-optimized

inference-optimization

Model card Files Files and versions

Qwen3-4B-Instruct-2507-optimized

Commit History

Update README.md

f15e1d3
verified

JDCentral commited on Jul 30

Update README.md

12ac19c
verified

JDCentral commited on Jul 30

Add optimized CUDA kernels (RMSNorm, MLP) and patched Qwen3 modeling file

e36ec14
verified

Khanin Udomchoksakul commited on Jul 9

initial commit

be68006
verified

Khanin Udomchoksakul commited on Jul 9