InferenceX
by
Home
Overview
Dashboard
Comparisons
About
Star
1,358
中文
Select Chart
Inference Performance
Accuracy Evals
Historical Trends
TCO Calculator
Chip Specs
Submissions
Back
·
Inference chart
Loading SKU navigator…
Loading point metadata…
Per-point
Request timeline
Aggregates across configs
Input sequence length distribution
Distribution
In-flight avg
Output sequence length distribution
Distribution
In-flight avg
Interactivity over time
— points
P75
P90
TTFT over time
TTFT
E2E
— points
P75
P90
KV cache utilization over time
Request queue depth
Queue depth
Completed
Prefix cache hit rate per interval
Throughput (input & decode)
Input
Decode
Cumulative prompt token source breakdown
Total unique input tokens over time
Unique input tokens in flight
