Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Decoding Latency on Llama-2-7B 96k sequence length v1 (inference)
Loading...
0.115
Decoding Latency (s)
PQCache
-0.01052
0.83674
1.684
2.53126
May 26, 2025
Decoding Latency (s)
Updated 4d ago
Evaluation Results
Method
Method
Links
Decoding Latency (s)
PQCache
Hardware=NVIDIA A100 (...
2025.05
0.115
TailorKV
Hardware=NVIDIA A100 (...
2025.05
0.132
TailorKV
Hardware=NVIDIA RTX 30...
2025.05
0.176
OffloadCache
Hardware=NVIDIA A100 (...
2025.05
3.253
Feedback
Search any
task
Search any
task