kendryte / Toucan-LLMLinks
Self-trained Large Language Models based on Meta LLaMa
☆30Updated 2 years ago
Alternatives and similar repositories for Toucan-LLM
Users that are interested in Toucan-LLM are comparing it to the libraries listed below
Sorting:
- prebuild package for cross compiling riscv☆17Updated 3 years ago
- Zhouyi model zoo☆102Updated 4 months ago
- ☆78Updated last year
- 将MNN拆解的简易前向推理框架(for study!)☆23Updated 4 years ago
- linux bsp app & sample for axpi (ax620a)☆36Updated 2 years ago
- ncnn benchmark on various single board computers☆162Updated 2 years ago
- DDK for Rockchip NPU☆67Updated 4 years ago
- Reverse engineering the V831 npu☆94Updated 4 years ago
- ☆24Updated 2 years ago
- ncnn和pnnx格式编辑器☆137Updated last year
- A converter for llama2.c legacy models to ncnn models.☆80Updated last year
- GPT2⚡NCNN⚡中文对话⚡x86⚡Android☆81Updated 3 years ago
- Explore LLM model deployment based on AXera's AI chips☆117Updated last week
- Efficient inference of large language models.☆149Updated 3 weeks ago
- Tengine Convert Tool supports converting multi framworks' models into tmfile that suitable for Tengine-Lite AI framework.☆92Updated 4 years ago
- Snapdragon Neural Processing Engine (SNPE) SDKThe Snapdragon Neural Processing Engine (SNPE) is a Qualcomm Snapdragon software accelerate…☆35Updated 3 years ago
- benchmark models for TNN, ncnn, MNN☆20Updated 5 years ago
- Inference TinyLlama models on ncnn☆24Updated 2 years ago
- the C++ version of Seq2Seq with ncnn☆23Updated 4 years ago
- a simple general program language☆99Updated last month
- ☆15Updated 3 years ago
- Benchmark your NCNN models on 3DS(or crash)☆10Updated last year
- Whisper in TensorRT-LLM☆16Updated 2 years ago
- Infere RWKV on NCNN☆49Updated last year
- An optimized neural network operator library for chips base on Xuantie CPU.☆95Updated last year
- Kendryte K510 Documents☆43Updated 2 years ago
- a lightweight deep learning framework for CSK60XX serial products☆25Updated last year
- ☆124Updated last year
- Open deep learning compiler stack for cpu, gpu and specialized accelerators☆33Updated 2 years ago
- autoTVM神经网络推理代码优化搜索演示,基于tvm编译开源模型centerface,并使用autoTVM搜索最优推理代码, 最终部署编译为c++代码,演示平台是cuda,可以是其他平台,例如树莓派,安卓手机,苹果手机.Thi is a demonstration of …☆28Updated 4 years ago