Alternatives

Products that do what Introducing QVAL does

Massive-parallel evaluation of parameter space on GPU

18F
80% faster, 50% less memory, 0% loss of accuracy Llama finetuning▲385
Hi HN! I'm just sharing a project I've been working on during the LLM Efficiency Challenge - you can now finetune Llama with QLoRA 5x faster than Huggingface's original implementation on your own local GPU. Some highlights: 1. Manual autograd engine - hand derived backprop steps. 2. QLoRA / LoRA 80% faster, 50% less memory. 3. All kernels written in OpenAI's Triton language. 4. 0% loss in accuracy - no approximation methods - all exact. 5. No change of hardware necessary. Supports NVIDIA GPUs since 2018+. CUDA 7.5+. 6. Flash Attention support via Xformers. 7. Supports 4bit and 16bit…
2023 · github.com
2CF
Cuq – Formal Verification of Rust GPU Kernels▲94
Oct 2025 · github.com
3IV
I've built a locally running Perplexity clone▲669
The video demo runs a 7b Model on a normal gaming GPU. I think it already works quite well (accounting for the limited hardware power). :)
2024 · github.com
4FL
Finetune LLaMA-7B on commodity GPUs using your own text▲449
I've been playing around with https://github.com/zphang/minimal-llama/ and https://github.com/tloen/alpaca-lora/blob/main/finetune.py, and wanted to create a simple UI where you can just paste text, tweak the parameters, and finetune the model quickly using a modern GPU. To prepare the data, simply separate your text with two blank lines. There's an inference tab, so you can test how the tuned model behaves. This is my first foray into the world of LLM finetuning, Python, Torch, Transformers, LoRA, PEFT, and Gradio. Enjoy!
2023 · github.com
5AG
A GPU-accelerated binary vector index▲65
This is a vector index I built that supports insertion and k-nearest neighbors (k-NN) querying, optimized for GPUs. It operates entirely in CUDA and can process queries on half a billion vectors in under 200 milliseconds. The codebase is structured as a standalone library with an HTTP API for remote access. It’s intended for high-performance search tasks—think similarity search, AI model retrieval, or reinforcement learning replay buffers. The codebase is located at https://github.com/rodlaf/BinaryGPUIndex.
2025 · rlafuente.com
6AP
A physically-based GPU ray tracer written in Julia▲198
We ported pbrt-v4 to Julia and built it into a Makie backend. Any Makie plot can now be rendered with physically-based path tracing. Julia compiles user-defined physics directly into GPU kernels, so anyone can extend the ray tracer with new materials and media - a black hole with gravitational lensing is ~200 lines of Julia. Runs on AMD, NVIDIA, and CPU via KernelAbstractions.jl, with Metal coming soon. Demo scenes: github.com/SimonDanisch/RayDemo
Feb 2026 · makie.org
7VA
Vector - A High-Level Programming Language for GPU Computing▲142
2013 · zhehaomao.com
8MD
my database engine for GPU▲364
2012 · sourceforge.net
9IM
I made a GPU VRAM calculator for transformer-based models▲135
2023 · vram.asmirnov.xyz
10SA
Squey, an open-source GPU-accelerated data visualization software▲66
While we hope you'll find it quite useful already, there is plenty of room for improvement so we greatly appreciate your feedback!
2024 · squey.org
11PC
Parsing CSV files with GPU▲123
2015 · github.com
12IB
I built a tensor library from scratch in C++/CUDA▲119
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
13
Shoehorn – Quantize any model down to run on your machine▲97
Working on Mac, Linux, and Windows now. I include a simple GUI to find new models and get things built and set up. It is working quite well across a few models for me. The GitHub README and DESIGN.md files go into detail of the how/why and it's working remarkably well so far. https://github.com/notactuallytreyanastasio/shoehorn
20d ago · notactuallytreyanastasio.github.io
14RQ
Run Qwen3-Next-80B on 8GB GPU at 1tok/2s throughput▲123
Sep 2025 · github.com
15
XY – A Fast, composable, GPU-accelerated interactive plotting library▲136
Ultra-fast and customizable Python charts. Contribute to reflex-dev/xy development by creating an account on GitHub.
Jul 2026 · github.com
16
Fine-tune an 8B model on a 4 GB laptop GPU▲139
Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU. - MakazhanAlpamys/Soup
Aug 2026 · github.com
17
Modal Notebooks▲140
High-performance, collaborative GPU notebooks in the cloud
Sep 2025
18
Qwen3.8-Flash-Next▲108
The open-weight preview of Qwen4
11d ago · qwen.ai
19AM
A Modern C/C++ build tools (Simple, Fast, Cross-platform)▲89
2019 · xmake.io
20PF
Pisa – Full Text Search Engine Written in C++▲96
2020 · github.com
21MA
Metashade – a Pythonic GPU shading/compute EDSL▲47
Superficially, it may look similar to Nvidia's Warp or OpenAI's Triton, but instead of transpiling a subset of Python to the target language, it implements dynamic codegen in pure Python. These slides discuss the existing GPU programming solutions and make a case for Metashade's approach: https://docs.google.com/presentation/d/e/2PACX-1vQtYIwXIkMnV...
2024 · github.com
22IV
I've made a GPU-based wavelet spectrogram tool for birdsongs▲34
2022 · github.com
23AL
A Language for Programming GPUs▲12
2019 · dev.to
24MA
MeTA: A Modern C++ Data Sciences Toolkit▲39
2014 · meta-toolkit.github.io

Ranked by how close each launch is in meaning, then by votes. Refine with a description →