Performance Analysis Python Packages

py-spy

Sampling profiler for Python programs

scalene

Scalene: a high-performance, high-precision CPU, GPU, and memory profiler for Python with AI-powered optimization proposals

llnl-hatchet

Graph-indexed Pandas DataFrames for analyzing hierarchical performance data

caliper-reader

Caliper is an instrumentation and performance profiling library

torchfunc-nightly

PyTorch functions and utilities to make your life easier

perfplot

:chart_with_upwards_trend: Performance analysis for Python snippets

triton-model-analyzer

Triton Model Analyzer is a CLI tool to help with better understanding of the compute and memory requirements of the Triton Inference Server models.

loopy

A code generator for array-based code on CPUs and GPUs

javacore-analyser

This is a tool to analyse IBM Javacore files and provide the report used to analyse hang/outage and performance issues.

fastapi-profiler-lite

A lightweight, zero-configuration performance profiler for FastAPI applications

cutracer

A dynamic binary instrumentation tool for tracing and analyzing GPU kernel instructions.

pg-diag

PostgreSQL diagnostic tool

bigo

Measures empirical computational complexity (in both time and space) of functions

flameox

Runtime evidence that helps agents trace, profile, and burn down hotspots in application and native code, GPU kernels, and inference stacks.

py-spy-asyncio

Sampling profiler for Python programs

fundamentalanalysis

Transparent and Efficient Financial Analysis

hatchet

Analyze graph/hierarchical performance data using pandas dataframes

timeit-decorator

A versatile timing decorator

pycubexr

pyCubexR is a Python package for reading the Cube4 (.cubex) file format.

osaca

Open Source Architecture Code Analyzer

perflens

Real-time Linux perf profiling in your browser. A tiny static C agent streams perf data from any ARM or x86 Linux device, big-endian included, and a Python server renders live flame graphs, function tables and line-level annotated source. Session replay, perf.data import, and an MCP server for AI agents.

slurmpast

Why your Slurm jobs failed, and what to ask for next time.

flameshow

A terminal Flamegraph viewer.

sparkhistogram

Includes notes on using Apache Spark, with drill down on Spark for Physics, how to run TPCDS on PySpark, how to create histograms with Spark. Also tools for stress testing, measuring CPUs' performance, and I/O latency heat maps. Jupyter notebooks examples for using various DB systems.