Optimizing diffusion for production-ready speeds
☆41Jan 10, 2026Updated 9 months ago
Alternatives and similar repositories for productionizing-diffusion
Users that are interested in productionizing-diffusion are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Minimal repository to demonstrate fast LoRA inference with Flux family of models.☆32Jul 23, 2025Updated last year
- StableFused is a toy library for experimenting with Diffusion Models, inspired by various sources.☆15Nov 2, 2023Updated 2 years ago
- Tensara's GPU programming problems☆20Apr 23, 2026Updated 6 months ago
- Easy recipes to speed up latency of Flux, QwenImage, and LTX-2 with NVFP4 and MXFP8 on Blackwell.☆14Apr 10, 2026Updated 6 months ago
- EleutherAI ML Performance reading group repository (slides, meeting recordings, annotated papers)☆38Mar 20, 2026Updated 7 months ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- Companion code for Grokking Megakernels: fuse an entire LLM forward pass into a single CUDA kernel☆31Feb 9, 2026Updated 8 months ago
- a repo to study TensorRT Plugin☆11Apr 30, 2025Updated last year
- Just another reasonably minimal repo for class-conditional training of pixel-space diffusion transformers.☆159May 29, 2025Updated last year
- kernelboard is the webapp for https://www.gpumode.com☆20Updated this week
- A film that never stops playing, that anyone can write.☆21Oct 22, 2026Updated last week
- ☆80Dec 27, 2024Updated last year
- Native Blackwell (sm_100) tcgen05 training backward for the gated-linear-recurrence family (GDN/KDA/GLA/SSD/LA), plus a contract-grade ve…☆15Oct 18, 2026Updated last week
- [NOTE] I do not have enough ressources to maintain VMS, please use Ostris's AI-Tookit instead☆43Oct 3, 2025Updated last year
- Row-wise block scaling for fp8 quantization matrix multiplication. Solution to GPU mode AMD challenge.☆19Feb 9, 2026Updated 8 months ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Making Flux go brrr on GPUs.☆174Jan 5, 2026Updated 9 months ago
- Benchmark tests supporting the TiledCUDA library.☆19Nov 19, 2024Updated last year
- Interactive version of the CuTe layout paper☆56Apr 14, 2026Updated 6 months ago
- Keeping track of placements details.☆21Jul 18, 2024Updated 2 years ago
- Implementation of "SCEdit: Efficient and Controllable Image Diffusion Generation via Skip Connection Editing"☆85Dec 26, 2023Updated 2 years ago
- A series of high-performance GEMM (General Matrix Multiply) implementations Iteratively optimised for H100 GPUs in Pure CUDA.☆83Feb 18, 2026Updated 8 months ago
- Official code for the transformer LLM experiments in the paper [Evolution Strategies at the Hyperscale](https://arxiv.org/abs/2511.16652)…☆16Apr 14, 2026Updated 6 months ago
- ☆49Feb 23, 2025Updated last year
- ☆14Jan 13, 2026Updated 9 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆18Dec 2, 2024Updated last year
- End-to-end recipes for optimizing diffusion models with torchao and diffusers (inference and FP8 training).☆396Jan 8, 2026Updated 9 months ago
- (WIP) Parallel inference for black-forest-labs' FLUX model.☆19Nov 18, 2024Updated last year
- Personal solutions to the Triton Puzzles☆22Jul 18, 2024Updated 2 years ago
- ☆40Updated this week
- Building an Image-to-Video (I2V) Model from Scratch☆30Jul 18, 2026Updated 3 months ago
- Nitro-T is a family of text-to-image diffusion models focused on highly efficient training.☆42Jun 4, 2026Updated 4 months ago
- ☆50Jun 7, 2025Updated last year
- a size profiler for cuda binary☆74Oct 3, 2026Updated 3 weeks ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- TritonParse: A Compiler Tracer, Visualizer, and Reproducer for Triton Kernels☆229Oct 20, 2026Updated last week
- Minimal TPU implementation with 8x8 systolic array and PyTorch integration☆71Jan 26, 2026Updated 9 months ago
- A Pure JAX AsyncRL stack☆23Sep 7, 2026Updated last month
- CuratorKIT : Data curation and synthetic data generation for LLM post-training.☆31Oct 13, 2026Updated 2 weeks ago
- Blog Archives☆18Mar 3, 2024Updated 2 years ago
- Shor's algorithm simulation using CUDA☆20Nov 10, 2019Updated 6 years ago
- patches for huggingface transformers to save memory☆37May 9, 2026Updated 5 months ago