This repository has been archived by the owner on Aug 30, 2024. It is now read-only.
[Neural Speed] Support continuous batching + beam search inference in LLAMA #428
Job | Run time |
---|---|
1s | |
1s | |
1s | |
3s |
Job | Run time |
---|---|
1s | |
1s | |
1s | |
3s |