This repository has been archived by the owner on Oct 25, 2024. It is now read-only.
[LLM Runtime] enable MHA fusion for gptneox&dolly&starcoder&llama2-70b#567
Merged
VincyZhang merged 17 commits intomainfrom mha_fusionNov 1, 2023
+290-162
Commits
Commits on Oct 27, 2023
- committed
- committed
- authored
- committed
- committed
Merge branch 'mha_fusion' of https://github.com/intel/intel-extension-for-transformers into mha_fusion
committed
Commits on Oct 30, 2023
- authored
- committed
- committed
Merge branch 'mha_fusion' of https://github.com/intel/intel-extension-for-transformers into mha_fusion
committed