Lightweight Python Wrapper for OpenVINO, enabling LLM inference on NPUs
☆30Dec 17, 2024Updated last year
Alternatives and similar repositories for nitro
Users that are interested in nitro are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆13May 11, 2023Updated 3 years ago
- BlockCIrculantRNN (LSTM and GRU) using TensorFlow☆14Oct 30, 2018Updated 7 years ago
- ☆54May 19, 2025Updated last year
- (WIP) Parallel inference for black-forest-labs' FLUX model.☆19Nov 18, 2024Updated last year
- This repository contains the official implementation for the ECCV'22 paper, "SPIN: An Empirical Evaluation on Sharing Parameters of Isotr…☆20Sep 9, 2023Updated 2 years ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- A forked version of flux-fast that makes flux-fast even faster with cache-dit, 3.3x speedup on NVIDIA L20.☆24Jul 18, 2025Updated last year
- ☆19Oct 6, 2025Updated 10 months ago
- ☆23Aug 14, 2024Updated last year
- 使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention☆82Aug 12, 2024Updated 2 years ago
- Quantized Attention on GPU☆45Nov 22, 2024Updated last year
- Multi-Layer Key-Value sharing experiments on Pythia models☆34Jun 14, 2024Updated 2 years ago
- Cluster doctor skills☆14May 23, 2026Updated 2 months ago
- A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters☆58May 3, 2026Updated 3 months ago
- ☆16Aug 19, 2024Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Lightweight framework for 3D rendering.☆12Jun 14, 2026Updated 2 months ago
- Magicube is a high-performance library for quantized sparse matrix operations (SpMM and SDDMM) of deep learning on Tensor Cores.☆92Nov 23, 2022Updated 3 years ago
- A side project that follows all the acceleration tricks in tinyllama, with the minimal modification to the huggingface transformers code.☆13Sep 2, 2024Updated last year
- Codeplay's tutorial LLDB-MSP430 - as presented at the 2016 EuroLLVM Developers' Meeting in Barcelona.☆10Mar 15, 2016Updated 10 years ago
- 很好用的tnn classify demo☆11Mar 24, 2021Updated 5 years ago
- ☆12Jan 18, 2023Updated 3 years ago
- Community maintained hardware plugin for vLLM on AWS Neuron☆47Jul 21, 2026Updated 3 weeks ago
- Systems Programming UIUC FA 2016☆13Feb 24, 2017Updated 9 years ago
- SGLang kernel library for NPU☆173Updated this week
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- ☆21Updated this week
- Tools and APIs to develop weavers for the LARA language (LARA Compiler, LARA Interpreter, Weaver Generator, etc...)☆16Updated this week
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆345Jul 2, 2024Updated 2 years ago
- DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.☆58Aug 21, 2024Updated last year
- Low-Rank Llama Custom Training☆23Mar 27, 2024Updated 2 years ago
- ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM☆11Jul 24, 2020Updated 6 years ago
- Multi-DNN Inference Engine for Heterogeneous Mobile Processors☆39Jul 24, 2024Updated 2 years ago
- Pytorch Optimizer for Simulated Annealing☆26Jan 8, 2018Updated 8 years ago
- ☆15May 13, 2024Updated 2 years 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.
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆117Aug 4, 2026Updated last week
- Unlimited Vector Extension with Data Streaming Support☆12Nov 25, 2024Updated last year
- Test Orchestrator for Performance and Scalability of AI pLatforms☆18Jun 23, 2026Updated last month
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆160Aug 21, 2025Updated 11 months ago
- IntelliJ platform plugin for Wavefront OBJ format☆15Jul 4, 2026Updated last month
- ☆20May 11, 2026Updated 3 months ago
- Based on ARMv8, mainly referring to xv6 and Linux kernel☆10Aug 1, 2022Updated 4 years ago