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.☆46Feb 27, 2025Updated last year
- Several optimization methods of half-precision general matrix vector multiplication (HGEMV) using CUDA core.☆77Sep 8, 2024Updated 2 years ago
- ☆34Feb 3, 2025Updated last year
- Several optimization methods of half-precision general matrix multiplication (HGEMM) using tensor core with WMMA API and MMA PTX instruct…☆574Sep 8, 2024Updated 2 years ago
- ☆271Jul 11, 2024Updated 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.
- Multiple GEMM operators are constructed with cutlass to support LLM inference.☆20Aug 3, 2025Updated last year
- ☆123May 16, 2025Updated last year
- Implement Flash Attention using Cute.☆113Dec 17, 2024Updated last year
- Quantized Attention on GPU☆45Nov 22, 2024Updated 2 years ago
- A practical way of learning Swizzle☆45Feb 3, 2025Updated last year
- Examples of CUDA implementations by Cutlass CuTe☆284Jul 1, 2025Updated last year
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆96Jun 21, 2026Updated 5 months ago
- ☆10Oct 30, 2024Updated 2 years ago
- DeeperGEMM: crazy optimized version☆85May 5, 2025Updated last year
- 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.
- A novel and efficient post-training INT6 quantization framework tailored for LLM inference.☆11Aug 29, 2026Updated 2 months ago
- CUTLASS and CuTe Examples☆143Nov 30, 2025Updated 11 months ago
- ☆20Dec 24, 2024Updated last year
- Matrix Multiply-Accumulate with CUDA and WMMA( Tensor Core)☆150Aug 18, 2020Updated 6 years ago
- 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
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆158May 10, 2025Updated last year
- Yinghan's Code Sample☆369Jul 25, 2022Updated 4 years ago
- Efficient and unified implementations for TopK-based sparse attention☆42Jul 10, 2026Updated 4 months ago
- SGEMM optimization with cuda step by step☆24Mar 23, 2024Updated 2 years 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.
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆130Jul 13, 2024Updated 2 years ago
- 方便扩展的Cuda算子理解和优化框架,仅用在学习使用☆18Jun 13, 2024Updated 2 years ago
- Benchmark tests supporting the TiledCUDA library.☆19Nov 19, 2024Updated 2 years ago
- A Easy-to-understand TensorOp Matmul Tutorial☆460Mar 5, 2026Updated 8 months ago
- Standalone Flash Attention v2 kernel without libtorch dependency☆113Sep 10, 2024Updated 2 years ago
- Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.☆15Aug 31, 2023Updated 3 years ago
- flash attention tutorial written in python, triton, cuda, cutlass☆541Nov 9, 2026Updated last week
- ⚡️Qwen-Image 4.8x🎉 speedup with Hybrid Acceleration for low VRAM GPUs☆17Oct 24, 2025Updated last year
- High performance RMSNorm Implement by using SM Core Storage(Registers and Shared Memory)☆31Jan 22, 2026Updated 9 months ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Optimizing SGEMM kernel functions on NVIDIA GPUs to a close-to-cuBLAS performance.☆430Jan 2, 2025Updated last year
- PyTorch bindings for CUTLASS grouped GEMM.☆157May 29, 2025Updated last year
- ☆159Mar 18, 2024Updated 2 years ago
- A curated list for Efficient Large Language Models☆11Mar 25, 2024Updated 2 years ago
- ☆195May 11, 2026Updated 6 months ago
- 使用 cutlass 实现 flash-attention 精简版,具有教学意义☆59Aug 12, 2024Updated 2 years ago
- Awesome code, projects, books, etc. related to CUDA☆50Aug 9, 2026Updated 3 months ago
Are these results useful?