Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
LLM Inference on Merge
Loading...
1.16
Goodput (req/s)
AugServe
-0.0048
0.2976
0.6
0.9024
Dec 3, 2025
Goodput (req/s)
Updated 4d ago
Evaluation Results
Method
Method
Links
Goodput (req/s)
AugServe
Request rate=3, CV=1,...
2025.12
1.16
AugServe
Request rate=2, CV=1.5...
2025.12
1.15
AugServe
Request rate=2, CV=1,...
2025.12
0.87
AugServe
Request rate=3, CV=1.5...
2025.12
0.58
AugServe
Request rate=2, CV=2,...
2025.12
0.47
AugServe
Request rate=3, CV=2,...
2025.12
0.35
InferCept
Request rate=2, CV=1,...
2025.12
0.28
vLLM
Request rate=2, CV=1,...
2025.12
0.22
InferCept
Request rate=3, CV=1,...
2025.12
0.2
vLLM
Request rate=3, CV=1,...
2025.12
0.15
InferCept
Request rate=2, CV=1.5...
2025.12
0.13
InferCept
Request rate=3, CV=1.5...
2025.12
0.11
vLLM
Request rate=2, CV=1.5...
2025.12
0.1
InferCept
Request rate=2, CV=2,...
2025.12
0.08
vLLM
Request rate=3, CV=1.5...
2025.12
0.07
InferCept
Request rate=3, CV=2,...
2025.12
0.06
vLLM
Request rate=2, CV=2,...
2025.12
0.05
vLLM
Request rate=3, CV=2,...
2025.12
0.04
Feedback
Search any
task
Search any
task