Add Softmax kernel in Triton. Use softmax kernel and argmax in Llama generation.py. + Small changes#11
Open
catherinelee274 wants to merge 12 commits intotriton-lang:mainfrom
Open
Add Softmax kernel in Triton. Use softmax kernel and argmax in Llama generation.py. + Small changes#11catherinelee274 wants to merge 12 commits intotriton-lang:mainfrom
catherinelee274 wants to merge 12 commits intotriton-lang:mainfrom
Commits
Commits on Sep 20, 2024
- committed
- committed
- committed
Commits on Sep 23, 2024
- committed