Bruce-Lee-LY / flash_attention_inferenceLinks
Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.
☆38Updated 3 months ago
Alternatives and similar repositories for flash_attention_inference
Users that are interested in flash_attention_inference are comparing it to the libraries listed below
Sorting:
- ☆96Updated 9 months ago
- ☆139Updated last year
- 使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention☆71Updated 10 months ago
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆92Updated 3 weeks ago
- ☆148Updated 5 months ago
- Standalone Flash Attention v2 kernel without libtorch dependency☆110Updated 9 months ago
- ☆77Updated last month
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆109Updated 11 months ago
- ☆122Updated 6 months ago
- ☆97Updated 2 months ago
- Implement Flash Attention using Cute.☆87Updated 6 months ago
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆80Updated last month
- Benchmark code for the "Online normalizer calculation for softmax" paper☆94Updated 6 years ago
- ☆135Updated last year
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆128Updated 2 months ago
- Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.☆38Updated 2 weeks ago
- ☆86Updated 2 months ago
- ☆58Updated 7 months ago
- ☆212Updated 11 months ago
- An easy-to-use package for implementing SmoothQuant for LLMs☆100Updated 2 months ago
- Examples of CUDA implementations by Cutlass CuTe☆197Updated 4 months ago
- 使用 cutlass 实现 flash-attention 精简版,具有教学意义☆42Updated 10 months ago
- ☆29Updated 4 months ago
- ☆34Updated last year
- Several optimization methods of half-precision general matrix vector multiplication (HGEMV) using CUDA core.☆62Updated 9 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 4 months ago
- A lightweight design for computation-communication overlap.☆143Updated this week
- play gemm with tvm☆91Updated last year
- ☆128Updated 6 months ago
- llama INT4 cuda inference with AWQ☆54Updated 5 months ago