Alternatives
Products that do what Graphsignal – ML profiler to speed up training and inference does
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…
- 1
- 2CW
Creator here. I built ChartGPU because I kept hitting the same wall: charting libraries that claim to be "fast" but choke past 100K data points. The core insight: Canvas2D is fundamentally CPU-bound. Even WebGL chart libraries still do most computation on the CPU. So I moved everything to the GPU via WebGPU: - LTTB downsampling runs as a compute shader - Hit-testing for tooltips/hover is GPU-accelerated - Rendering uses instanced draws (one draw call per series) The result: 1M points at 60fps with smooth zoom/pan. Live demo:…
Jan 2026 · github.com
- 3
- 4TO
Mar 2026 · github.com
- 5PC
Hey 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…
2025 · github.com
- 6
- 7
- 8IB
Hi HN, Over the past few months, I've been building `dsc`, a tensor library from scratch in C++/CUDA. My main focus has been on getting the basics right, prioritizing a clean API, simplicity, and clear observability for running small LLMs locally. The key features are: - C++ core with CUDA support written from scratch. - A familiar, PyTorch-like Python API. - Runs real models: it's complete enough to load a model like Qwen from HuggingFace and run inference on both CUDA and CPU with a single line change[1]. - Simple, built-in observability for both Python and C++. Next on the roadmap is…
2025 · github.com
- 9
- 10
- 11
- 12SH
Morning HN. I often found myself wondering "how much does this code segment take in terms of total runtime" and it's often quite annoying to figure out with optimizations enabled, especially when working on something new or testing someone else's implementation without the proper tooling set up. Wanted to have a single include lib that would allow us to write something like: ``` PROFILE("Loop 1") for (...) // some work ``` and have the next expression automatically record time & dump results to a table. Wrote a few macros to do exactly that a few months back, but they were…
2025 · github.com
- 13
- 14
Interactive, animated architecture maps for any Hugging Face model — and whether it fits on your GPU.
19d ago · modelmap.cc
- 15CR
The goal of Carton is to let you use a single interface to run any machine learning model from any programming language. It’s currently difficult to integrate models that use different technologies (e.g. TensorRT, Ludwig, TorchScript, JAX, GGML, etc) into your application, especially if you’re not using Python. Even if you learn the details of integrating each of these frameworks, running multiple frameworks in one process can cause hard-to-debug crashes. Ideally, the ML framework a model was developed in should just be an implementation detail. Carton lets you decouple your application from…
2023 · carton.run
- 16
- 17PM
Hey HN! We’re Vaibhav and Marcello. We’re building Plexe (https://github.com/plexe-ai/plexe), an open-source agent that turns natural language task descriptions into trained ML models. Here’s a video walkthrough: https://www.youtube.com/watch?v=bUwCSglhcXY. There are all kinds of uses for ML models that never get realized because the process of making them is messy and convoluted. You can spend months trying to find the data, clean it, experiment with models and deploy to production, only to find out that your project has been binned for taking so long.…
2025 · github.com
- 18BV
Vision models have been gaining popularity as a replacement for traditional OCR. Especially with Gemini 2.0 becoming cost competitive with the cloud platforms. We've been continuously evaluating different models since we released the Zerox package last year (https://github.com/getomni-ai/zerox). And we wanted to put some numbers behind it. So we’re open sourcing our internal OCR benchmark + evaluation datasets. Full writeup + data explorer here: https://getomni.ai/ocr-benchmark Github: https://github.com/getomni-ai/benchmark Huggingface:…
2025 · getomni.ai
- 19LO
Hi HN, I’m Joe. My friends Matthew, Jake and I are building Luminal (https://luminalai.com/), a GPU compiler for automatically generating fast GPU kernels for AI models. It uses search-based compilation to achieve high performance. We take high level model code, like you'd have in PyTorch, and generate very fast GPU code. We do that without using LLMs or AI - rather, we pose it as a search problem. Our compiler builds a search space, generates millions of possible kernels, and then searches through it to minimize runtime. You can try out a demo in `demos/matmul` on mac to…
2025 · github.com
- 20GL
Hey HN! We're Paul, Preston, and Daniel from Zep. We've just open-sourced Graphiti, a Python library for building temporal Knowledge Graphs using LLMs. Graphiti helps you create and query graphs that evolve over time. Knowledge Graphs have been explored extensively for information retrieval. What makes Graphiti unique is its ability to build a knowledge graph while handling changing relationships and maintaining historical context. At Zep, we build a memory layer for LLM applications. Developers use Zep to recall relevant user information from past conversations without including the entire…
2024 · github.com
- 21K2
Hey Hacker News! We are excited to share our open-source project, KTransformers, a flexible framework designed for cutting-edge LLM inference optimizations! Leveraging state-of-the-art kernels from llamafile and marlin, KTransformers seamlessly enhances the performance of HuggingFace Transformers, making it possible to operate large 236B MoE models or extremely long 1M context locally with promising speed. KTransformers is a Python-centric framework designed with extensibility at its core. By implementing and injecting an optimized module with a single line of code, users gain access to a…
2024 · github.com
- 22MB
Hey everyone, ML Blocks is a node-based workflow builder to create multi-modal AI workflows without writing any code. You connect blocks that call various visual models like GPT4v, Segment Anything, Dino etc. along with basic image processing blocks like resize, invert color, blur, crop, and several others. The idea is to make it easier to deploy multi-step image processing workflows, without needing to spin up endless custom OpenCV cloud functions to glue together AI models. Usually, even if you're using cloud inference servers like Replicate, you still need to write your own image…
2024 · mlblocks.com
- 23UD
Hey HN! I’m the founder of Unify, and we’ve just released our Model Hub, which provides a collection of LLM endpoints with live runtime benchmarks all plotted across time: https://unify.ai/hub A key finding is that static tabular runtime benchmarks for LLMs simply do not work. It’s necessary to take a time-series perspective, and plot the variations through time. We currently have 21 models provided by: Anyscale, Perplexity AI, Replicate, Together AI, OctoAI, Mistral AI and OpenAI, with more on the roadmap. We test across different regions (Asia, US, Europe), with varied…
2024
- 24EW
2023 · lastmileai.dev
Ranked by how close each launch is in meaning, then by votes. Refine with a description →