Alternatives and similar repositories for llama.cpp:

Users that are interested in llama.cpp are comparing it to the libraries listed below

• MegEngine / mperf
  mperf是一个面向移动/嵌入式平台的算子性能调优工具箱
  ☆179Updated last year
• nihui / vkpeak
  A tool which profiles Vulkan devices to find their peak capacities
  ☆114Updated 6 months ago
• nihui / ruapu
  Detect CPU features with single-file
  ☆385Updated this week
• daquexian / web-model-converter
  ☆40Updated 2 years ago
• MARD1NO / CUDA-PPT
  ☆87Updated last year
• waau / qualcomm-nnlib
  Qualcomm Hexagon NN Offload Framework
  ☆42Updated 4 years ago
• daquexian / faster-rwkv
  ☆124Updated last year
• MollySophia / rwkv-ncnn
  Infere RWKV on NCNN
  ☆48Updated 6 months ago
• xxxxyu / FlexNN
  Code for ACM MobiCom 2024 paper "FlexNN: Efficient and Adaptive DNN Inference on Memory-Constrained Edge Devices"
  ☆51Updated 2 months ago
• QianyanTech / NBAssembler
  Assembler and Decompiler for NVIDIA (Maxwell Pascal Volta Turing Ampere) GPUs.
  ☆77Updated 2 years ago
• MollySophia / rwkv-qualcomm
  Inference RWKV v5, v6 and v7 with Qualcomm AI Engine Direct SDK
  ☆60Updated this week
• lx200916 / ChatBotApp
  ☆28Updated 4 months ago
• willhua / QualcommOpenCLSDKNote
  The note of Qualcomm OpenCL SDK
  ☆32Updated 6 years ago
• nihui / ncnn-android-vkpeak
  ☆18Updated 4 years ago
• lrw04 / llama2.c-to-ncnn
  A converter for llama2.c legacy models to ncnn models.
  ☆87Updated last year
• gfvvz / triton-learning-materials
  Triton Compiler related materials.
  ☆28Updated 2 months ago
• EdVince / NeRF-NCNN
  NeRF in NCNN with c++ & vulkan
  ☆67Updated last year
• UbiquitousLearning / Mandheling-DSP-Training
  The open-source project for "Mandheling: Mixed-Precision On-Device DNN Training with DSP Offloading"[MobiCom'2022]
  ☆18Updated 2 years ago
• chraac / llama.cpp
  LLM inference in C/C++
  ☆34Updated last week
• pigirons / conv3x3_m1
  This is a demo how to write a high performance convolution run on apple silicon
  ☆54Updated 3 years ago
• zhouwg / ggml-hexagon
  focus on implementation of ggml-hexagon backend for Qualcomm's Hexagon NPU, details can be seen at https://github.com/zhouwg/ggml-hexagon…
  ☆13Updated this week
• TiledTensor / TiledCUDA
  We invite you to visit and follow our new repository at https://github.com/microsoft/TileFusion. TiledCUDA is a highly efficient kernel …
  ☆179Updated 2 months ago
• yester31 / Cutlass_EX
  study of cutlass
  ☆21Updated 4 months ago
• EdVince / diffusers-ncnn
  ☆84Updated 2 years ago
• tfruan2000 / mlsys-study-note
  My study note for mlsys
  ☆14Updated 4 months ago
• BBuf / how-to-optimize-gemm
  ☆95Updated 3 years ago
• xlite-dev / hgemm-mma
  ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.
  ☆63Updated this week
• Cambricon / mlu-ops
  Efficient operation implementation based on the Cambricon Machine Learning Unit (MLU) .
  ☆110Updated this week
• Mengjintao / FastCNN
  ☆19Updated 2 years ago
• OpenPPL / CuAssembler
  An unofficial cuda assembler, for all generations of SASS, hopefully ：）
  ☆82Updated 2 years ago