dianhsu / transformer-cpp-cpu

Related projects: ⓘ

• dianhsu / swin-transformer-cpp
  Swin Transformer C++ Implementation
  ☆53Updated 3 years ago
• LeiWang1999 / tvm_gpu_gemm
  play gemm with tvm
  ☆81Updated last year
• InfiniTensor / RefactorGraph
  分层解耦的深度学习推理引擎
  ☆58Updated 3 weeks ago
• AyakaGEMM / Hands-on-GEMM
  ☆90Updated 6 months ago
• DD-DuDa / Cute-Gemm-Optimization
  ☆15Updated last week
• weishengying / tiny-flash-attention
  使用 cutlass 实现 flash-attention 精简版，具有教学意义
  ☆29Updated last month
• OpenPPL / ppl.pmx
  ☆56Updated last week
• Bruce-Lee-LY / cuda_hgemv
  Several optimization methods of half-precision general matrix vector multiplication (HGEMV) using CUDA core.
  ☆40Updated last week
• JieRen98 / SGEMM-SASS-Annotation
  ☆18Updated 3 years ago
• HuPengsheet / EasyNN
  EasyNN是一个面向教学而开发的神经网络推理框架，旨在让大家0基础也能自主完成推理框架编写！
  ☆22Updated 3 weeks ago
• 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.
  ☆20Updated last week
• tlc-pack / libflash_attn
  Standalone Flash Attention v2 kernel without libtorch dependency
  ☆93Updated last week
• ShaYeBuHui01 / flash_attention_inference
  Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.
  ☆13Updated last year
• BBuf / how-to-optimize-gemm
  ☆92Updated 3 years ago
• MARD1NO / CUDA-PPT
  ☆77Updated last year
• tlc-pack / cutlass_fpA_intB_gemm
  A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer
  ☆82Updated 6 months ago
• OpenPPL / ppl.llm.kernel.cuda
  ☆133Updated 2 months ago
• luchangli03 / onnxsim_large_model
  simplify >2GB large onnx model
  ☆41Updated 6 months ago
• OpenPPL / ppl.kernel.cuda
  ☆32Updated 3 months ago
• zeroine / cutlass-cute-sample
  ☆18Updated 5 months ago
• weishengying / cutlass_flash_atten_fp8
  使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention
  ☆46Updated last month
• sunkx109 / llama.cpp
  llama 2 Inference
  ☆35Updated 10 months ago
• reed-lau / cute-gemm
  ☆70Updated 6 months ago
• CalvinXKY / BasicCUDA
  A tutorial for CUDA&PyTorch
  ☆110Updated last week
• njuhope / cuda_sgemm
  ☆100Updated 5 months ago
• KarhouTam / cuda-kernels
  Some common CUDA kernel implementations (Not the fastest).
  ☆11Updated last month
• gty111 / GEMM_MMA
  Optimize GEMM with tensorcore step by step
  ☆11Updated 9 months ago
• mrzhuzhe / riven
  CPU Memory Compiler and Parallel programing
  ☆24Updated 2 months ago
• GetUpEarlier / minit
  ☆20Updated 3 months ago
• jundaf2 / CUDA-INT8-GEMM
  CUDA 8-bit Tensor Core Matrix Multiplication based on m16n16k16 WMMA API
  ☆22Updated last year