a minimal paged attention implementation
☆20Jan 30, 2026Updated 8 months ago
Alternatives and similar repositories for nano-paged-attention
Users that are interested in nano-paged-attention are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- writing really fast kernels☆20Sep 12, 2026Updated 3 weeks ago
- a simple c++ inference engine for gpt based architecture☆41Dec 10, 2025Updated 10 months ago
- ☆18Jun 26, 2024Updated 2 years ago
- ☆15Jul 25, 2025Updated last year
- ☆134Dec 9, 2025Updated 10 months ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- a LLM inference engine to run on consumer hardware☆48Apr 15, 2026Updated 5 months ago
- ☆51Aug 17, 2026Updated last month
- ☆17Dec 28, 2024Updated last year
- Flash Attention from scratch, tiled CUDA forward kernel, online softmax with running max and correction factor, recomputation trick in ba…☆19Mar 6, 2026Updated 7 months ago
- ☆12Jun 14, 2024Updated 2 years ago
- ☆27Jun 7, 2026Updated 4 months ago
- ☆20Apr 26, 2026Updated 5 months ago
- Optimizing diffusion for production-ready speeds☆41Jan 10, 2026Updated 9 months ago
- MathNet: A Data-Centric Approach, Dataset and Benchmark Model to Advance Mathematical Expression Recognition☆10Mar 19, 2025Updated last year
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- A high-performance job scheduler designed for microsecond latency (<5us P50 latency) and massive concurrency (highest throughput : 2M+ jo…☆30Jan 11, 2026Updated 8 months ago
- raft based distributed kv store☆29Jan 6, 2026Updated 9 months ago
- Implementation of GALS (GNSS-Augmented LiDAR SLAM)☆15Jul 5, 2022Updated 4 years ago
- ☆13Apr 7, 2025Updated last year
- 化学式自动配平计算器☆11Jul 28, 2022Updated 4 years ago
- fast, observable reverse proxy with its own config language.☆40Apr 27, 2026Updated 5 months ago
- [NeurIPS'25 Spotlight🔥]Official implementation of Uni-MuMER: Unified Multi-Task Fine-Tuning of Vision-Language Model for Handwritten Ma…☆45May 11, 2026Updated 4 months ago
- "JABAS: Joint Adaptive Batching and Automatic Scaling for DNN Training on Heterogeneous GPUs" (EuroSys '25)☆16Apr 7, 2025Updated last year
- Official codebase for the MLSys 2026 paper "IntAttention: A Fully Integer Attention Pipeline for Efficient Edge Inference". It enables hi…☆22May 29, 2026Updated 4 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- My submission for the GPUMODE/AMD fp8 mm challenge☆29Jun 4, 2025Updated last year
- serving a torch model using Celery, Redis and RabbitMQ to serve users asynchronously☆25Jan 21, 2024Updated 2 years ago
- egraph <-> json☆18Dec 29, 2025Updated 9 months ago
- It contains Data Augmentaion, Strided convolution, Batch Normalization, Leaky Relu, Global Average pooling, L2 Regularization, learning …☆12Jun 3, 2018Updated 8 years ago
- Hacks for PyTorch☆19Apr 18, 2023Updated 3 years ago
- A pure-Python implementation of the Nvidia CuTe layout algebra intended to be approachable and easy to learn.☆253Jun 29, 2026Updated 3 months ago
- a personal collection of my notes for ml sys☆124Sep 1, 2026Updated last month
- Official repository for the paper DynaPipe: Optimizing Multi-task Training through Dynamic Pipelines☆19Dec 8, 2023Updated 2 years ago
- Fused KL divergence from hidden states for knowledge distillation☆22Apr 28, 2026Updated 5 months ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Simple intermediate representation language for learning and research.☆22Mar 27, 2020Updated 6 years ago
- FlexiTokens☆23Dec 27, 2025Updated 9 months ago
- fastcv is a CUDA rewrite of the opencv filters with python bindings☆75Oct 10, 2025Updated last year
- Demo code for CVPR2023 paper "Sparsifiner: Learning Sparse Instance-Dependent Attention for Efficient Vision Transformers"☆15Jul 4, 2023Updated 3 years ago
- Using e-graphs to synthesize netlists from boolean logic.☆14Jul 26, 2023Updated 3 years ago
- A simple plugin to automatically restart the server after the server crashed☆10Aug 22, 2025Updated last year
- Perceptron-based branch predictor written in C++☆14Dec 14, 2016Updated 9 years ago