TPU inference for vLLM, with unified JAX and PyTorch support.
☆439Sep 24, 2026Updated this week
Alternatives and similar repositories for tpu-inference
Users that are interested in tpu-inference are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- JAX backend for SGL☆354Updated this week
- Tokamax: A GPU and TPU kernel library.☆303Updated this week
- ☆128Sep 5, 2026Updated 2 weeks ago
- torchax is a PyTorch frontend for JAX. It gives JAX the ability to author JAX programs using familiar PyTorch syntax. It also provides JA…☆245Sep 17, 2026Updated last week
- Minimal yet performant LLM examples in pure JAX☆284Aug 23, 2026Updated last month
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- ☆83Updated this week
- ☆389Updated this week
- Microbenchmarking hyperparameter tuning for JAX functions.☆24Aug 24, 2026Updated last month
- ☆28Updated this week
- A Lightweight LLM Post-Training Library☆2,460Updated this week
- JetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs wel…☆460Jan 5, 2026Updated 8 months ago
- A simple, performant, and scalable Jax LLM!☆2,428Updated this week
- a Jax quantization library☆136Updated this week
- High-performance large-scale embedding acceleration for JAX on Google TPU SparseCores.☆37Updated this week
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- A simplified and automated orchestration workflow to perform ML end-to-end (E2E) model tests and benchmarking on Cloud VMs across differe…☆64Updated this week
- Orbax provides common checkpointing and persistence utilities for JAX users☆533Updated this week
- Recipes for reproducing training and serving benchmarks for large machine learning models using GPUs on Google Cloud.☆140Sep 8, 2026Updated 2 weeks ago
- ☆592Jul 11, 2024Updated 2 years ago
- MLIR-based partitioning system☆213Updated this week
- xpk (Accelerated Processing Kit, pronounced x-p-k,) is a software tool to help Cloud developers to orchestrate training jobs on accelerat…☆194Aug 27, 2026Updated 3 weeks ago
- PyTorch/XLA integration with JetStream (https://github.com/google/JetStream) for LLM inference"☆85Dec 18, 2025Updated 9 months ago
- easydel jax kernels writen in triton for gpus and pallas for tpus☆31Sep 15, 2026Updated last week
- Minimal, lightweight JAX implementations of popular models.☆245May 29, 2026Updated 3 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Google TPU optimizations for transformers models☆136Jan 23, 2026Updated 8 months ago
- ☆15May 11, 2025Updated last year
- Package of Pathways-on-Cloud utilities☆33Updated this week
- Automatic differentiation for Triton Kernels☆29Aug 12, 2025Updated last year
- Testing framework for Deep Learning models (Tensorflow and PyTorch) on Google Cloud hardware accelerators (TPU and GPU)☆64Jul 22, 2026Updated 2 months ago
- Pax is a Jax-based machine learning framework for training large scale models. Pax allows for advanced and fully configurable experimenta…☆561Sep 16, 2026Updated last week
- A Python-embedded DSL that makes it easy to write fast, scalable ML kernels with minimal boilerplate.☆951Updated this week
- ☆32Sep 9, 2026Updated 2 weeks ago
- Open Source Continuous Inference Benchmark Research Platform — Kimi K3 2.8T, MiniMax M3, DeepSeekv4, GLM5 - GB200 NVL72 vs MI355X vs B200 …☆1,758Updated this week
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆2,512Updated this week
- PyTorch Single Controller☆1,078Updated this week
- EleutherAI ML Performance reading group repository (slides, meeting recordings, annotated papers)☆37Mar 20, 2026Updated 6 months ago
- JaxPP is a library for JAX that enables flexible MPMD pipeline parallelism for large-scale LLM training☆83Sep 18, 2026Updated last week
- FlashInfer: Kernel Library for LLM Serving☆6,502Updated this week
- NVIDIA Inference Xfer Library (NIXL)☆1,269Updated this week
- SGLang kernel library for Intel XPU☆36Updated this week