LATENCY & PERFORMANCEAI SRE

Batching

Batching processes multiple inference requests together to improve hardware utilization.

WHY IT MATTERS

Batching can raise throughput but may also add waiting time and worsen latency if tuned badly.

PRODUCTION EXAMPLE

Increasing batch size raises tokens/sec by 25% but adds 400ms to p95 TTFT for interactive users.

SRE DECISION

What throughput gain is worth the additional queueing latency for this workload?

REMEMBERBatching trades some immediacy for efficiency.
No uploads · No company data · No account required