benchmarking some transformer deployments
β26Dec 15, 2025Updated 11 months ago
Alternatives and similar repositories for transformer-benchmarks
Users that are interested in transformer-benchmarks are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Nod.ai π¦ version of π» . You probably want to start at https://github.com/nod-ai/shark for the product and the upstream IREE repository β¦β107Dec 15, 2025Updated 11 months ago
- Microbenchmarks showing relative performance of different Python functions/patterns.β13Oct 3, 2025Updated last year
- β15Mar 17, 2026Updated 8 months ago
- Wrappers for open source FPU hardware implementations.β37Nov 27, 2025Updated 11 months ago
- a simple end to end example of taking a ML graph (TF2 / PyTorch) and running it on a device [cpu, gpu]β37Jan 20, 2021Updated 5 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer β’ AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- β13Nov 25, 2019Updated 6 years ago
- [SIGMETRICS 2022] One Proxy Device Is Enough for Hardware-Aware Neural Architecture Searchβ13Nov 3, 2021Updated 5 years ago
- Official NVIDIA/srt-slurm sweep configs for benchmarking LLMs across NVIDIA GPUs and frameworks, spanning aggregated and disaggregated seβ¦β10Sep 18, 2026Updated 2 months ago
- Local-first, open-source Claude Science alternative. Web/ Desktop App. Claude Code/ Codex.β21Jul 1, 2026Updated 4 months ago
- β13Aug 6, 2019Updated 7 years ago
- Codebase associated with the PyTorch compiler tutorialβ47Sep 7, 2019Updated 7 years ago
- Advanced Formal Language Theory (263-5352-00L; FrΓΌhjahr 2023)β10Feb 21, 2023Updated 3 years ago
- A source-to-source compiler for optimizing CUDA dynamic parallelism by aggregating launchesβ15Jun 21, 2019Updated 7 years ago
- This project compares the performance of Swin-Transformer v2 implemented in JAX and PyTorch.β12Jun 8, 2022Updated 4 years ago
- Deploy on Railway without the complexity - Free Credits Offer β’ AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Roofline prototype for Armβ14Updated this week
- Library for length agnostic SIMD intrinsic support and the corresponding math operationsβ21Nov 15, 2021Updated 5 years ago
- GPT-jax based on the official huggingface libraryβ13Jun 22, 2021Updated 5 years ago
- [INACTIVE] A real-time, collaborative, HTML5 drawing widget powered by KineticJS / FabricJS and inspired by Literally Canvas.β10Feb 9, 2014Updated 12 years ago
- DICOM Analytics and Archiveβ11Nov 30, 2018Updated 7 years ago
- Canidadate for the Kaggle 2017 Data Science Bowl - Automatic detection of lung cancer from CT scansβ10Apr 7, 2017Updated 9 years ago
- Professional ZipChain infrastructure with ZipChain-optimized zipchain-optimization and enterprise scalable-architecture capabilitiesβ19May 12, 2026Updated 6 months ago
- Torch Frontend for IREEβ26Dec 21, 2023Updated 2 years ago
- doppioDB - A hardware accelerated databaseβ53May 2, 2017Updated 9 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer β’ AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- β19Oct 18, 2017Updated 9 years ago
- β11May 16, 2019Updated 7 years ago
- β18May 24, 2016Updated 10 years ago
- Heron: Automatically Constrained High-Performance Library Generation for Deep Learning Acceleratorsβ25Jan 30, 2024Updated 2 years ago
- β18Updated this week
- Professional QueueCore queuecore-engine with QueueCore-optimized scalable-architecture and enterprise intelligent-automation capabilitiesβ26May 12, 2026Updated 6 months ago
- Python backend for Annotator (http://github.com/nickstenning/annotator)β18Nov 21, 2010Updated 15 years ago
- OpenH264 decode raw h264 demo.β10Jul 8, 2017Updated 9 years ago
- β15Apr 10, 2026Updated 7 months ago
- GPU virtual machines on DigitalOcean Gradient AI β’ AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- This is the public repo for the MLPerf DeepCAM climate data segmentation proposal.β16Sep 30, 2025Updated last year
- self-hosted workspace for Google's Jules AI agentβ18Jul 4, 2026Updated 4 months ago
- β25Jun 24, 2026Updated 4 months ago
- β13Aug 23, 2019Updated 7 years ago
- π GPU load-balancing library for regular and irregular computations.β68Jun 25, 2026Updated 4 months ago
- DRA+RISC-V Exploration Frameworkβ25Jan 8, 2024Updated 2 years ago
- Code and sample images described in the paper "DeepScribe: Localization and Classification of Elamite Cuneiform Signs Via Deep Learning"β17Dec 29, 2024Updated last year
Are these results useful?