This repository has been archived by the owner on Aug 30, 2024.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 #412
Job | Run time |
---|---|
2m 3s | |
1m 38s | |
1m 24s | |
1m 16s | |
11m 7s | |
17m 28s |