zhouwg / ggml-hexagonLinks
reference implementation of the backend for llama.cpp on Android phone equipped with Qualcomm's Hexagon NPU, details can be seen at https://github.com/zhouwg/ggml-hexagon/discussions/18
☆23Updated this week
Alternatives and similar repositories for ggml-hexagon
Users that are interested in ggml-hexagon are comparing it to the libraries listed below
Sorting:
- LLM inference in C/C++☆42Updated last week
- Inference RWKV v5, v6 and v7 with Qualcomm AI Engine Direct SDK☆72Updated last week
- llm deploy project based onnx.☆42Updated 8 months ago
- llama 2 Inference☆41Updated last year
- mperf是一个面向移动/嵌入式平台的算子性能调优工具箱☆186Updated last year
- 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!☆31Updated 10 months ago
- Standalone Flash Attention v2 kernel without libtorch dependency☆110Updated 9 months ago
- FlagTree is a unified compiler for multiple AI chips, which is forked from triton-lang/triton.☆43Updated this week
- 使用 CUDA C++ 实现的 llama 模型推理框架☆57Updated 7 months ago
- ☆124Updated last year
- This repository is a read-only mirror of https://gitlab.arm.com/kleidi/kleidiai☆51Updated this week
- Sophgo AI chips driver and runtime library.☆21Updated this week
- ☆35Updated 2 months ago
- hands on model tuning with TVM and profile it on a Mac M1, x86 CPU, and GTX-1080 GPU.☆48Updated 2 years ago
- ☆69Updated this week
- ☆31Updated 9 months ago
- QAI AppBuilder is designed to help developers easily execute models on WoS and Linux platforms. It encapsulates the Qualcomm® AI Runtime …☆50Updated this week
- Assembler and Decompiler for NVIDIA (Maxwell Pascal Volta Turing Ampere) GPUs.☆80Updated 2 years ago
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆128Updated 2 months ago
- stable diffusion using mnn☆68Updated last year
- A converter for llama2.c legacy models to ncnn models.☆81Updated last year
- ☆58Updated 7 months ago
- VeriSilicon Tensor Interface Module☆235Updated 5 months ago
- ☆36Updated 8 months ago
- ☆29Updated 4 months ago
- ☆158Updated last week
- 分层解耦的深度学习推理引擎☆73Updated 4 months ago
- a tensor computing compiler based tile programming for gpu, cpu or tpu☆43Updated this week
- 机器学习编译 陈天奇☆35Updated 2 years ago
- ⚡️FFPA: Extend FlashAttention-2 with Split-D, achieve ~O(1) SRAM complexity for large headdim, 1.8x~3x↑ vs SDPA.☆186Updated last month