Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.
☆48Jun 11, 2025Updated last year
Alternatives and similar repositories for decoding_attention
Users that are interested in decoding_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:
- Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.☆45Feb 27, 2025Updated last year
- Multiple GEMM operators are constructed with cutlass to support LLM inference.☆20Aug 3, 2025Updated last year
- ☆271Jul 11, 2024Updated 2 years ago
- Several optimization methods of half-precision general matrix vector multiplication (HGEMV) using CUDA core.☆75Sep 8, 2024Updated last year
- Quantized Attention on GPU☆45Nov 22, 2024Updated last year
- 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.
- ☆122May 16, 2025Updated last year
- Implement Flash Attention using Cute.☆111Dec 17, 2024Updated last year
- Several optimization methods of half-precision general matrix multiplication (HGEMM) using tensor core with WMMA API and MMA PTX instruct…☆564Sep 8, 2024Updated last year
- ☆20Dec 24, 2024Updated last year
- SGEMM optimization with cuda step by step☆23Mar 23, 2024Updated 2 years ago
- DeeperGEMM: crazy optimized version☆86May 5, 2025Updated last year
- Awesome code, projects, books, etc. related to CUDA☆40Updated this week
- Standalone Flash Attention v2 kernel without libtorch dependency☆113Sep 10, 2024Updated last year
- We invite you to visit and follow our new repository at https://github.com/microsoft/TileFusion. TiledCUDA is a highly efficient kernel …☆192Jan 28, 2025Updated last year
- 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.
- Benchmark tests supporting the TiledCUDA library.☆19Nov 19, 2024Updated last year
- Examples of CUDA implementations by Cutlass CuTe☆281Jul 1, 2025Updated last year
- A practical way of learning Swizzle☆45Feb 3, 2025Updated last year
- 使用 cutlass 实现 flash-attention 精简版，具有教学意义☆59Aug 12, 2024Updated 2 years ago
- Quick and Self-Contained TensorRT Custom Plugin Implementation and Integration☆87May 26, 2025Updated last year
- ☆82Dec 27, 2024Updated last year
- Created a simple neural network using C++17 standard and the Eigen library that supports both forward and backward propagation.☆11Jul 27, 2024Updated 2 years ago
- Simple and efficient memory pool is implemented with C++11.☆10Jun 2, 2022Updated 4 years ago
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆96Jun 21, 2026Updated last month
- 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.
- CUTLASS and CuTe Examples☆137Nov 30, 2025Updated 8 months ago
- ☆157Mar 18, 2024Updated 2 years ago
- A unified programming framework for high and portable performance across FPGAs and GPUs☆11Mar 23, 2025Updated last year
- A collection of memory efficient attention operators implemented in the Triton language.☆305Jul 22, 2026Updated 3 weeks ago
- ☆14Nov 3, 2025Updated 9 months ago
- A Easy-to-understand TensorOp Matmul Tutorial☆450Mar 5, 2026Updated 5 months ago
- ☆117Jul 28, 2026Updated 2 weeks ago
- llama INT4 cuda inference with AWQ☆54Jan 20, 2025Updated last year
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆158May 10, 2025Updated last year
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- Flash Attention in ~100 lines of CUDA (forward pass only)☆1,175Dec 30, 2024Updated last year
- Dynamic Memory Management for Serving LLMs without PagedAttention☆512Jul 17, 2026Updated 3 weeks ago
- 使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention☆82Aug 12, 2024Updated 2 years ago
- Yinghan's Code Sample☆365Jul 25, 2022Updated 4 years ago
- ☆97Mar 26, 2025Updated last year
- 使用 CUDA C++ 实现的 llama 模型推理框架☆64Nov 8, 2024Updated last year
- ☆34Feb 3, 2025Updated last year