Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Inference Efficiency on 30k Context Length Llama-2-7B

6.6Inference Throughput (QPS)

Finetuning

0.5682.1343.75.266Mar 11, 2025
Updated 3d ago

Evaluation Results

MethodLinks
2025.03
6.6---
2025.03
3.4---
2025.03
1.5---
2025.03
0.8---
2025.03
--11
2025.03
--4.50.51
2025.03
---0.12
2025.03
--30.22