AlibabaPAI / FLASHNN

Related projects ⓘ

Alternatives and complementary repositories for FLASHNN

• Bruce-Lee-LY / flash_attention_inference
  Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.
  ☆29Updated 2 months ago
• weishengying / cutlass_flash_atten_fp8
  使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention
  ☆52Updated 3 months ago
• ColfaxResearch / cutlass-kernels
  ☆167Updated 4 months ago
• tlc-pack / libflash_attn
  Standalone Flash Attention v2 kernel without libtorch dependency
  ☆98Updated 2 months ago
• tgale96 / grouped_gemm
  PyTorch bindings for CUTLASS grouped GEMM.
  ☆53Updated 2 weeks ago
• tlc-pack / cutlass_fpA_intB_gemm
  A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer
  ☆85Updated 8 months ago
• FlagOpen / FlagAttention
  A collection of memory efficient attention operators implemented in the Triton language.
  ☆219Updated 5 months ago
• bytedance / flux
  A fast communication-overlapping library for tensor parallelism on GPUs.
  ☆224Updated 3 weeks ago
• microsoft / vattention
  Dynamic Memory Management for Serving LLMs without PagedAttention
  ☆238Updated last week
• wangsiping97 / FastGEMV
  High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.
  ☆90Updated 4 months ago
• HandH1998 / QQQ
  QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.
  ☆87Updated last month
• OpenPPL / ppl.nn.llm
  ☆140Updated 6 months ago
• 66RING / tiny-flash-attention
  flash attention tutorial written in python, triton, cuda, cutlass
  ☆202Updated 5 months ago
• TiledTensor / TiledCUDA
  TiledCUDA is a highly efficient kernel template library designed to elevate CUDA C’s level of abstraction for processing tiles.
  ☆154Updated this week
• fanshiqing / grouped_gemm
  PyTorch bindings for CUTLASS grouped GEMM.
  ☆68Updated 4 months ago
• madsys-dev / deepseekv2-profile
  ☆64Updated 3 months ago
• Bruce-Lee-LY / cuda_hgemv
  Several optimization methods of half-precision general matrix vector multiplication (HGEMV) using CUDA core.
  ☆49Updated 2 months ago
• ankan-ban / llama_cu_awq
  llama INT4 cuda inference with AWQ
  ☆48Updated 4 months ago
• DD-DuDa / Cute-Learning
  Examples of CUDA implementations by Cutlass CuTe
  ☆98Updated last week
• AniZpZ / AutoSmoothQuant
  An easy-to-use package for implementing SmoothQuant for LLMs
  ☆83Updated 6 months ago
• ColfaxResearch / cfx-article-src
  ☆48Updated this week
• MARD1NO / CUDA-PPT
  ☆79Updated last year
• LLMServe / SwiftTransformer
  High performance Transformer implementation in C++.
  ☆82Updated 2 months ago
• LeiWang1999 / AutoGPTQ.tvm
  GPTQ inference TVM kernel
  ☆36Updated 6 months ago
• sgl-project / sgl-learning-materials
  Materials for learning SGLang
  ☆96Updated this week
• OpenPPL / ppl.llm.kernel.cuda
  ☆138Updated 2 weeks ago
• usyd-fsalab / fp6_llm
  An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).
  ☆208Updated 3 weeks ago
• reed-lau / cute-gemm
  ☆79Updated 8 months ago
• LeiWang1999 / tvm_gpu_gemm
  play gemm with tvm
  ☆84Updated last year
• microsoft / SparTA
  ☆131Updated 3 months ago