Support qwen2-1.5b with fused decoderlayer optimization on NPU#11888
Merged
plusbang merged 6 commits intointel-analytics:mainfrom plusbang:qwen2_1.5b_fused_supportAug 22, 2024
+1,119-15
Commits
Commits on Aug 21, 2024
- committed
- committed
- committed
- committed
- committed
- committed
