This repository has been archived by the owner on Aug 30, 2024. It is now read-only.
[LLM Runtime] Support 3bits & 4bits GPTQ for gpt-j #278
Job | Run time |
---|---|
1m 49s | |
1m 32s | |
1m 23s | |
1m 12s | |
10m 59s | |
16m 55s |
Job | Run time |
---|---|
1m 49s | |
1m 32s | |
1m 23s | |
1m 12s | |
10m 59s | |
16m 55s |