Latency Python Packages

tcp-latency

Module and command-line tool to measure latency using TCP.

llama

Library for testing and measuring network loss and latency between distributed endpoints.

dns-benchmark-tool

deprecated — migrate to net-benchmark. see https://github.com/net-benchmark/net-benchmark

shredstream

Solana ShredStream SDK/Decoder for Python, enabling ultra-low latency Solana transaction streaming via UDP shreds from https://www.shredstream.com

net-benchmark

Network benchmarking suite for DNS, HTTP, and SSL — with DNSSEC validation, DoH/DoT support, high‑concurrency testing, and enterprise‑grade reporting.

osaca

Open Source Architecture Code Analyzer

percently

A fast and efficient percentile calculator written in Rust.

latency-monitor

Lightweight TCP and UDP latency monitoring tool, with pluggable interface for publishing metrics

aioprox

Async Python proxy manager with latency testing

lattice-transport

A complete transport layer for LLM traffic

connmonitor

A persistent monitor and aggregator of network statistics

modelping

⚡ Benchmark LLM, STT, and TTS inference latency across providers. Measure TTFT P50/P95/P99, full voice pipeline benchmarks, CI-ready.

infermark

Benchmark any OpenAI-compatible LLM endpoint. TTFT, inter-token latency, throughput, P50-P99 — in one command.

pytorchures

Measure execution times of every layer in your pytorch model.

llmperf

Benchmarking tool for stress testing self-hosted LLMs, Azure OpenAI, and OpenAI APIs. Measure latency, throughput, and optimize performance. 🚀

pavo-bench

A 50K-turn voice pipeline benchmark and an 85K-param meta-controller that cuts P95 latency 10.3% and energy 71% vs fixed cloud. TMLR 2026.

voice-budget

The only voice agent context manager with a TTFT feedback loop

do-latency

Digital Ocean latency checker helps to find fastest DO region from your location.

llcv

An Extensible Framework for Low-Latency Computer Vision Research :fast_forward:

nn-meter

A DNN inference latency prediction toolkit for accurately modeling and predicting the latency on diverse edge devices.

hdr-plot

A simple standalone script to plot HdrHistograms directly from the output of wrk load testing tool

peano

Measures performance and reports to InfluxDB

splleed

LLM Inference performance harness

lltune

LLTune tunes Linux servers for ultra-low latency workloads. It scans system state, generates a config, audits for risks, applies safe CPU/ memory/network/kernel/IRQ tuning with backups and rollback, and stages persistence services for reboot.