Refactor llama3 demo to the new generator API#16753
Open
mtairum wants to merge 39 commits intomainfrom mtairum/llama3_text_demo
+1,250-1,245
Commits
Commits on Feb 7, 2025
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
#0: Updated attention wo dense matmul program config to increase perf and reduce time to first token
committed- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
