Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
LLM Serving on Azure-Conv
Loading...
8.02
Throughput (req/s)
DUETSERVE
5.5968
6.2259
6.855
7.4841
Nov 6, 2025
Throughput (req/s)
TTFT (s)
TBT (ms)
Average GPU Utilization
Updated 1d ago
Evaluation Results
Method
Method
Links
Throughput (req/s)
TTFT (s)
TBT (ms)
Average GPU Utilization
DUETSERVE
Model=Qwen3-32B, Clust...
2025.11
8.02
58.9
104.7
93.5
DYNAMO
Model=Qwen3-32B, Clust...
2025.11
5.69
110.2
23.1
74.6
Feedback
Search any
task
Search any
task