Graphsignal – ML profiler to speed up training and inference
Hi, Graphsignal founder here. We've launched Graphsignal earlier this year to make machine learning profiling practical and easy to use. Basically, it enables the profile-optimize-benchmark loop. For example, making inference faster by optimizing an ML model, while still maintaining accuracy. We've make a lot of progress that I wanted to share. The profiler now natively supports TensorFlow, Keras, PyTorch, PyTorch Lightning, Hugging Face, XGBoost and JAX frameworks along with built-in support for distributed workloads. Profiles now include tracing information in chrome trace format. Process…
Graphsignal – ML profiler to speed up training and inference launched on July 4, 2022 with 16 votes, #821 of 2,916 launches that month and more than 75% of that year's launches. The site was still online in September 2026, 4 years on.
In plain words
Graphsignal is a machine learning profiler that helps developers optimize model training and inference speed while maintaining accuracy. It supports TensorFlow, Keras, PyTorch, PyTorch Lightning, Hugging Face, XGBoost, and JAX, with built-in distributed workload support. The tool provides detailed profiling data including process and GPU utilization metrics, chrome trace format tracing, and enables teams to share and monitor profiled workloads across long training runs.
written from the facts on this page · September 2026
From the sources
GPU Profiler for AI agents. Contribute to graphsignal/graphsignal development by creating an account on GitHub.
In the maker’s words, at launch
Hi, Graphsignal founder here. We've launched Graphsignal earlier this year to make machine learning profiling practical and easy to use. Basically, it enables the profile-optimize-benchmark loop. For example, making inference faster by optimizing an ML model, while still maintaining accuracy. We've make a lot of…
Does a similar job
all alternatives →
Graphsignal – Machine learning profiler for training and inference2022 · graphsignal.com · ▲35Hi HN, I'm the founder of Graphsignal (https://graphsignal.com). Graphsignal is a machine learning profiler. We've created it to make ML profiling simple and usable. It provides performance summaries, ML operation and kernel level statistics as well as detailed resource usage information necessary for making training and inference faster and more efficient. Profilers help fix performance issues, improve user experience and reduce computation costs. Such improvements benefit machine learning profoundly; model training jobs that run for hours or days could be made much shorter and…
Graphsignal – Production Model Monitoring: Anomalies, Drift, Exceptions2021 · github.com · ▲30GPU Profiler for AI agents. Contribute to graphsignal/graphsignal development by creating an account on GitHub.
Perforator – cluster-wide profiling tool for large data centers2025 · github.com · ▲78Hey HN! We are happy to share Perforator – our internal cluster-wide profiler with great support for native languages and a built-in AutoFDO pipeline to simplify sPGO builds. Perforator allows you to profile most binaries without having to recompile or adjust the build process. We use it at Yandex to profile each pod inside a large cluster at modest speed (99Hz), collecting petabytes of profiles every day. There's a blog post about it at https://medium.com/yandex/yandexs-high-performance-profiler-.... Inspired by Google-Wide Profiling, we started continuous profiling…
graphql-request-profiler – a small GraphQL performance analysis plugin2022 · github.com · ▲17Easy to use GraphQL performance analysis utility for tracing resolver execution time - Econify/graphql-request-profiler
HuggingFace – Fast tokenization library for deep-learning NLP pipelines2020 · github.com · ▲168💥 Fast State-of-the-Art Tokenizers optimized for Research and Production - huggingface/tokenizers
CUDA Profiler for Production InferenceJun 2026 · github.com · ▲6Graphsignal Profiler. Contribute to graphsignal/graphsignal-profiler development by creating an account on GitHub.
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 21d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 30d ago · world.pixverse.video
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, July 2022
the whole month →
Locofy.ai▲720Hey there, I am Honey - Co-founder at Locofy. We, along with other makers, have been building Locofy.ai to help massively accelerate the builders - the designers, developers, product managers & founders, and we're excited to share it today with the HN Community. Locofy.ai simply converts designs into production-ready frontend code for web and mobile apps. It adapts to your preferred design tools, tech stack, and workflows with ease and lets you launch upto 4x faster, while letting designers design the way they want and giving high-quality responsive code that developers love. With this…
Dev tools · 2022 · locofy.ai
- PO
Life & fun · 2022 · justine.lol
Open Source realtime backend in 1 file. Contribute to pocketbase/pocketbase development by creating an account on GitHub.
Dev tools · 2022 · github.com
ruttl▲552Visual & Design Feedback Tool that helps you review design, content and report bugs on websites, applications, PDFs and images.
Dev tools · 2022 · ruttl.com
Hello, HN - I wanted to share this puzzle game I made during my vacation. I'm rather fond of the pipes puzzle where your goal is to restore a scrambled network of connections by rotating tiles. It's usually played on a grid of squares and this all started when I decided to make a programmatic solver for that kind of puzzle. Then I realized that with some minor changes the solver could generate new puzzle instances. I thought about what kind of puzzle to make and someone suggested a hexagonal grid. Adapting the generator wasn't too hard but then I had to create a way to play this variant. So…
Life & fun · 2022 · hexapipes.vercel.app
We're building Parsnip to create a "tech tree" of cooking skills that allows anyone to level up on the building blocks of cooking knowledge while tracking their progress over time. It took us a few iterations to figure out the right product; here's the story of our latest pivot: [https://parsnip.substack.com/p/a-new-hope] The goal is to create a personalized way to learn any recipe on the Internet, then use this as a springboard to help home cooks of all levels solve the problem of repeated meal planning in a 10x better way:…
Work · 2022 · parsnip.ai