Alternatives and similar repositories for cvGPUSpeedup

Users that are interested in cvGPUSpeedup are comparing it to the libraries listed below

• onnx / neural-compressor
  Model compression for ONNX
  ☆99Updated last year
• caibucai22 / awesome-cuda
  Awesome code, projects, books, etc. related to CUDA
  ☆26Updated 3 months ago
• triple-Mu / TensorRT2ONNX
  A tool convert TensorRT engine/plan to a fake onnx
  ☆41Updated 3 years ago
• triple-Mu / HunyuanDiT-TensorRT-libtorch
  HunyuanDiT with TensorRT and libtorch
  ☆18Updated last year
• Libraries-Openly-Fused / FusedKernelLibrary
  Implementation of a methodology that allows all sorts of user defined GPU kernel fusion, for non CUDA programmers.
  ☆32Updated this week
• dusty-nv / NanoDB
  Zero-copy multimodal vector DB with CUDA and CLIP/SigLIP
  ☆63Updated 7 months ago
• megvii-research / IntLLaMA
  IntLLaMA: A fast and light quantization solution for LLaMA
  ☆18Updated 2 years ago
• ahennequ / cuda-tensorcores-register-mapping
  ☆19Updated 3 years ago
• meta-pytorch / tokenizers
  C++ implementations for various tokenizers (sentencepiece, tiktoken etc).
  ☆42Updated last week
• NVlabs / EfficientDL
  ☆34Updated 5 months ago
• latentCall145 / channels-last-groupnorm
  A CUDA kernel for NHWC GroupNorm for PyTorch
  ☆21Updated last year
• tile-ai / tvm
  Open deep learning compiler stack for cpu, gpu and specialized accelerators
  ☆19Updated this week
• Bruce-Lee-LY / decoding_attention
  Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.
  ☆45Updated 5 months ago
• zhenhuaw-me / onnxcli
  ONNX Command-Line Toolbox
  ☆35Updated last year
• lucasjinreal / wanwu_release
  Wanwu models release, code will be released soon
  ☆24Updated 3 years ago
• GindaChen / FlexFlashAttention3
  FlexAttention w/ FlashAttention3 Support
  ☆27Updated last year
• FeiGeChuanShu / trt2023
  NVIDIA TensorRT Hackathon 2023复赛选题：通义千问Qwen-7B用TensorRT-LLM模型搭建及优化
  ☆43Updated 2 years ago
• CVHub520 / efficientvit
  EfficientViT is a new family of vision models for efficient high-resolution vision.
  ☆29Updated 2 years ago
• SkyworkAI / vllm
  A high-throughput and memory-efficient inference and serving engine for LLMs
  ☆16Updated last year
• Oneflow-Inc / OneFlow-Pruning
  [CVPR-2023] Towards Any Structural Pruning
  ☆17Updated 2 years ago
• simveit / persistent_dense_gemm
  Persistent dense gemm for Hopper in `CuTeDSL`
  ☆15Updated 4 months ago
• gpu-mode / triton-tutorials
  ☆15Updated 6 months ago
• Oneflow-Inc / oneflow-lite
  ☆18Updated last year
• TRT2022 / ControlNet_TensorRT
  天池 NVIDIA TensorRT Hackathon 2023 —— 生成式AI模型优化赛 初赛第三名方案
  ☆50Updated 2 years ago
• TiledTensor / TiledBench
  Benchmark tests supporting the TiledCUDA library.
  ☆17Updated last year
• yester31 / Cutlass_EX
  study of cutlass
  ☆22Updated last year
• jimmy-evo / opencl_kernels
  An easy way to run, test, benchmark and tune OpenCL kernel files
  ☆24Updated 2 years ago
• li199603 / sgemm_with_cuda
  SGEMM optimization with cuda step by step
  ☆21Updated last year
• yuzhenmao / IceFormer
  Implementation of IceFormer: Accelerated Inference with Long-Sequence Transformers on CPUs (ICLR 2024).
  ☆25Updated 4 months ago
• tlc-pack / libflash_attn
  Standalone Flash Attention v2 kernel without libtorch dependency
  ☆112Updated last year