xlite-dev / ffpa-attnLinks
⚡️FFPA: Extend FlashAttention-2 with Split-D, achieve ~O(1) SRAM complexity for large headdim, 1.8x~3x↑ vs SDPA.🎉
☆194Updated 2 months ago
Alternatives and similar repositories for ffpa-attn
Users that are interested in ffpa-attn are comparing it to the libraries listed below
Sorting:
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆93Updated 2 months ago
- ☆92Updated 4 months ago
- ☆96Updated 10 months ago
- Implement Flash Attention using Cute.☆92Updated 7 months ago
- ☆89Updated 2 months ago
- 使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention☆74Updated 11 months ago
- We invite you to visit and follow our new repository at https://github.com/microsoft/TileFusion. TiledCUDA is a highly efficient kernel …☆183Updated 6 months ago
- flash attention tutorial written in python, triton, cuda, cutlass☆398Updated 2 months ago
- A collection of memory efficient attention operators implemented in the Triton language.☆275Updated last year
- ☆51Updated 2 weeks ago
- A lightweight design for computation-communication overlap.☆155Updated last month
- Examples of CUDA implementations by Cutlass CuTe☆214Updated last month
- ☆60Updated 3 months ago
- Standalone Flash Attention v2 kernel without libtorch dependency☆111Updated 10 months ago
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆137Updated 3 months ago
- Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.☆39Updated 5 months ago
- ☆145Updated 5 months ago
- ☆137Updated last year
- A Easy-to-understand TensorOp Matmul Tutorial☆369Updated 10 months ago
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆94Updated 3 weeks ago
- ☆149Updated 6 months ago
- Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.☆40Updated last month
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆113Updated last year
- Benchmark code for the "Online normalizer calculation for softmax" paper☆95Updated 7 years ago
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆260Updated 3 weeks ago
- ☆227Updated last year
- Tutorials for writing high-performance GPU operators in AI frameworks.☆129Updated last year
- ☆139Updated last year
- An easy-to-use package for implementing SmoothQuant for LLMs☆103Updated 3 months ago
- DeeperGEMM: crazy optimized version☆71Updated 3 months ago