sophgo / LLM-TPU
Run generative AI models in sophgo BM1684X
☆103Updated this week
Related projects: ⓘ
- run ChatGLM2-6B in BM1684X☆48Updated 6 months ago
- llm-export can export llm model to onnx.☆193Updated this week
- simplify >2GB large onnx model☆41Updated 6 months ago
- export llama to onnx☆91Updated 3 months ago
- LLaMa/RWKV onnx models, quantization and testcase☆345Updated last year
- run chatglm3-6b in BM1684X☆38Updated 6 months ago
- A Toolkit to Help Optimize Large Onnx Model☆135Updated 4 months ago
- stable diffusion using mnn☆58Updated 11 months ago
- 基于MNN-llm的安卓手机部署大语言模型:Qwen1.5-0.5B-Chat☆40Updated 5 months ago
- ☆123Updated 9 months ago
- DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including …☆130Updated 3 weeks ago
- DeepSparkHub selects hundreds of application algorithms and models, covering various fields of AI and general-purpose computing, to suppo…☆46Updated this week
- Machine learning compiler based on MLIR for Sophgo TPU.☆579Updated this week
- ☆123Updated 3 months ago
- ☆140Updated 4 months ago
- This is the official PyTorch implementation of "LLMC: Benchmarking Large Language Model Quantization with a Versatile Compression Toolkit…☆227Updated this week
- A whisper repo for TPU☆10Updated 3 months ago
- ☆56Updated this week
- Explore LLM model deployment based on AXera's AI chips☆48Updated 2 weeks ago
- DDK for Rockchip NPU☆58Updated 3 years ago
- ☆17Updated this week
- qwen2 and llama3 cpp implementation☆34Updated 3 months ago
- ☆148Updated this week
- 本项目是一个通过文字生成图片的项目,基于开源模型Stable Diffusion V1.5生成可以在手机的CPU和NPU上运行的模型,包括其配套的模型运行框架。☆87Updated 5 months ago
- a lightweight deep learning framework for CSK60XX serial products☆23Updated 2 months ago
- PaddlePaddle custom device implementaion. (『飞桨』自定义硬件接入实现)☆67Updated last week
- A quantization algorithm for LLM☆98Updated 2 months ago
- Compare multiple optimization methods on triton to imporve model service performance☆46Updated 8 months ago
- ☆10Updated this week
- ☆90Updated last year