n4nAI

Topic

Batch Inference Throughput Benchmarks

12 posts on batch inference throughput benchmarks — part of benchmarks & performance on the n4n AI blog.

Benchmarks & performanceAnalysis

Why larger batches don't always mean higher throughput

Explains why increasing batch size eventually stops improving LLM inference throughput, with concrete tradeoffs between latency and hardware limits.

5 min read
Benchmarks & performanceComparison

Tokens per second at batch size 1 vs batch size 64

A practical tokens per second batch size comparison: batch size 1 versus 64 across latency, cost, ergonomics, and limits for LLM inference.

5 min read
Benchmarks & performanceGuide

Throughput vs latency: the batch size tradeoff explained

Practitioner guide to the throughput latency batch size tradeoff: measure baseline, sweep batches, find the knee, and implement adaptive batching.

4 min read
Benchmarks & performanceComparison

Throughput benchmark: single-GPU vs multi-GPU inference

Practical comparison of single-GPU vs multi-GPU throughput for LLM inference: scaling efficiency, cost, latency, and which setup to pick for your workload.

4 min read
Benchmarks & performanceAnalysis

Measuring throughput ceiling on 8x H100 clusters

Practical analysis of measuring the real 8x H100 cluster throughput ceiling for batch inference: parallelism, saturation testing, and tradeoffs.

5 min read
Benchmarks & performanceGuide

How continuous batching improves LLM throughput

Continuous batching LLM throughput gains come from dynamic scheduling. This guide shows how to measure, implement, and tune it for production inference serving.

5 min read
Benchmarks & performanceComparison

Batch throughput benchmark: Mixtral vs dense 70B models

Practical batch throughput comparison of Mixtral 8x7B MoE against dense 70B models across cost, latency, and ergonomics for LLM inference pipelines.

4 min read
Benchmarks & performanceHow-to

Batch size tuning for maximum LLM serving throughput

A practical, measurement-driven guide to batch size tuning throughput for LLM serving: step-by-step sweeps, memory limits, and validation under load.

4 min read
Benchmarks & performanceComparison

Batch inference throughput: vLLM vs TensorRT-LLM

A practitioner's head-to-head comparison of vLLM vs TensorRT-LLM throughput for batch inference across capabilities, cost, latency, ergonomics, ecosystem, and hard limits.

5 min read
Benchmarks & performanceAnalysis

Batch inference throughput for Llama 3.1 70B at scale

Analysis of Llama 3.1 70B throughput at scale: continuous batching, KV cache limits, and parallel strategies that decide batch inference cost and latency.

5 min read
Benchmarks & performanceComparison

Batch inference throughput benchmark on H100 vs A100

Direct H100 vs A100 throughput benchmark for batch LLM inference across capabilities, cost, latency, and ergonomics, with a head-to-head table and verdict.

4 min read
Benchmarks & performanceAnalysis

Batch inference throughput benchmark for DeepSeek V3

Analysis of DeepSeek V3 throughput benchmark: MoE batching behavior, KV cache limits, and how to measure real-world inference performance.

5 min read