latentCall145 / channels-last-groupnorm

Related projects ⓘ

Alternatives and complementary repositories for channels-last-groupnorm

• 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
• caiwanxianhust / FasterLLaMA
  使用 CUDA C++ 实现的 llama 模型推理框架
  ☆24Updated 2 weeks ago
• tlc-pack / libflash_attn
  Standalone Flash Attention v2 kernel without libtorch dependency
  ☆98Updated 2 months ago
• CalebDu / Awesome-Cute
  ☆16Updated this week
• Bruce-Lee-LY / decoding_attention
  Decoding Attention is specially optimized for multi head attention (MHA) using CUDA core for the decoding stage of LLM inference.
  ☆25Updated 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
• InternLM / turbomind
  ☆35Updated 2 weeks ago
• LeiWang1999 / TVM.CMakeExtend
  Tutorials of Extending and importing TVM with CMAKE Include dependency.
  ☆11Updated last month
• LeiWang1999 / AutoGPTQ.tvm
  GPTQ inference TVM kernel
  ☆36Updated 6 months 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.
  ☆29Updated 2 months ago
• tgale96 / grouped_gemm
  PyTorch bindings for CUTLASS grouped GEMM.
  ☆53Updated 3 weeks ago
• Bruce-Lee-LY / cuda_hgemv
  Several optimization methods of half-precision general matrix vector multiplication (HGEMV) using CUDA core.
  ☆50Updated 2 months ago
• AlibabaPAI / FLASHNN
  ☆79Updated 2 months ago
• feifeibear / ChituAttention
  Quantized Attention on GPU
  ☆30Updated 2 weeks ago
• mlc-ai / xgrammar
  Efficient, Flexible and Portable Structured Generation
  ☆53Updated this week
• LeiWang1999 / Stream-k.tvm
  ☆18Updated last month
• zeroine / cutlass-cute-sample
  ☆22Updated 7 months ago
• LeiWang1999 / tvm_gpu_gemm
  play gemm with tvm
  ☆84Updated last year
• weishengying / tiny-flash-attention
  使用 cutlass 实现 flash-attention 精简版，具有教学意义
  ☆32Updated 3 months ago
• TiledTensor / TiledCUDA
  TiledCUDA is a highly efficient kernel template library designed to elevate CUDA C’s level of abstraction for processing tiles.
  ☆156Updated this week
• OpenPPL / ppl.kernel.cuda
  ☆32Updated last month
• leimao / Nsight-Compute-Docker-Image
  Nsight Compute in Docker
  ☆11Updated 11 months ago
• chengzeyi / piflux
  (WIP) Parallel inference for black-forest-labs' FLUX model.
  ☆11Updated this week
• MARD1NO / CUDA-PPT
  ☆79Updated last year
• OpenPPL / ppl.pmx
  ☆57Updated 2 weeks ago
• Oneflow-Inc / serving
  OneFlow Serving
  ☆20Updated 9 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
• yester31 / Cutlass_EX
  study of cutlass
  ☆19Updated last week