Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Snippet Generation on Industry Workload Llama-3.1-8B
Loading...
8.67
Throughput (A100)
BatchLLM
5.3212
6.1906
7.06
7.9294
Nov 29, 2024
Throughput (A100)
Throughput (MI200)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Throughput (A100)
Throughput (MI200)
BatchLLM
2024.11
8.67
4.24
vLLM + c + p
chunked-prefill=true,...
2024.11
6.71
3.36
vLLM + p
prefix-caching=true
2024.11
6.2
3.27
vLLM + c
chunked-prefill=true
2024.11
5.48
2.84
vLLM
2024.11
5.45
2.75
Feedback
Search any
task
Search any
task