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…
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
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 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 and GPU utilization data has been extended as well. It is now possible to monitor all run metrics. Useful for long runs. Profiled workloads are now sharable across teams and publicly (if enabled). I'm excited to show it here and appreciate any thoughts, comments and feedback!
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, July 2022
the whole month →
- PO
Life & fun · 2022 · justine.lol
- PO
Dev tools · 2022 · github.com
- PP
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
- PD
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