throughput

A new kind of Progress Bar, with real-time throughput, ETA, and very cool animations!

LLM Serving Performance Evaluation Harness

An intelligent tuner for vLLM that automatically monitors GPU metrics, uses Bayesian optimization to tune parameters

【一个小工具】用最短的代码完成对模型的分析，包含 ImageNet Val、FLOPs、Params、Throuthput、CAM 等

ROS Network Analysis Package: This is a ROS package that provide tools to analyze the wireless network such as the signal quality, latency, throughput, link utilization, connection rates, error metrics, etc., between two ROS nodes/computers/machines.

Fast and reliable distributed systems in Python

RPC protocol based on kafka. Horizontally scalable, fault-tolerant, wicked fast, just like kafka.

High performance functions to work with the async IO.

Command-line tool to monitor Redis in real-time

BRRRRRRRRRRRRRRRRRRRRRR

A python script to parse through ns2 tracefiles, calculate the throughput and plot the throughputs against packetsizes using gnuplot.

High-precision edge and on-device LLM inference profiler calculating TTFT, TPOT, tokens/second throughput, and percentile jitter distributions (P50/P90/P99).

High-precision edge and on-device LLM inference profiler calculating TTFT, TPOT, tokens/second throughput, and percentile jitter distributions (P50/P90/P99).

When reasoning pays off: chart-backed guidance for reasoning effort, cost, latency, and capacity planning.

LLM inference benchmarking toolkit. Measure TTFT, inter-token latency, throughput, and P50–P99 across concurrency levels.

evaluate llm's generation speed via API

The Kafka Partition Count Recommender [Multithreading] tool analyzes historical topic consumption, identifies peak throughput over # of days, scales it for future demand, and translates it into optimal partition counts—delivering automated, data-driven topic sizing that ensures performance and scalability.

Bottleneck-analysis tool for a serial production line: load your measured cycle times, validate the model against real output, and quantify the ROI of fixing the constraint.

Reproducible, zero-dependency benchmark of local LLMs on Ollama: speed (tok/s), energy, reasoning and code quality, driven by a single-source-of-truth config pipeline.

Software that calculates and plot Throughput, Delay and other metrics from a tcpdump script.