MooreThreads / torch_musaLinks
torch_musa is an open source repository based on PyTorch, which can make full use of the super computing power of MooreThreads graphics cards.
☆434Updated 2 weeks ago
Alternatives and similar repositories for torch_musa
Users that are interested in torch_musa are comparing it to the libraries listed below
Sorting:
- a lightweight LLM model inference framework☆738Updated last year
- Ascend PyTorch adapter (torch_npu). Mirror of https://gitee.com/ascend/pytorch☆413Updated this week
- A high-throughput and memory-efficient inference and serving engine for LLMs☆56Updated 10 months ago
- Machine learning compiler based on MLIR for Sophgo TPU.☆789Updated last week
- MUSA Templates for Linear Algebra Subroutines☆31Updated 6 months ago
- FlagGems is an operator library for large language models implemented in the Triton Language.☆661Updated this week
- PaddlePaddle custom device implementaion. (『飞桨』自定义硬件接入实现)☆94Updated this week
- llm-export can export llm model to onnx.☆304Updated 7 months ago
- optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052☆475Updated last year
- Run generative AI models in sophgo BM1684X/BM1688☆236Updated last week
- MegCC是一个运行时超轻量,高效,移植简单的深度学习模型编译器☆487Updated 10 months ago
- ☆615Updated last year
- A CPU tool for benchmarking the peak of floating points☆559Updated last month
- Triton Documentation in Chinese Simplified / Triton 中文文档☆80Updated 4 months ago
- C++ implementation of Qwen-LM☆609Updated 8 months ago
- Efficient operation implementation based on the Cambricon Machine Learning Unit (MLU) .☆127Updated last week
- A powerful toolkit for compressing large models including LLM, VLM, and video generation models.☆550Updated last week
- ☆485Updated 3 weeks ago
- ☆50Updated last year
- cudnn_frontend provides a c++ wrapper for the cudnn backend API and samples on how to use it☆608Updated 2 weeks ago
- PyTorch Neural Network eXchange☆618Updated last week
- FlagScale is a large model toolkit based on open-sourced projects.☆347Updated this week
- ☆118Updated last year
- Low-bit LLM inference on CPU/NPU with lookup table☆845Updated 2 months ago
- how to learn PyTorch and OneFlow☆449Updated last year
- ☆140Updated last year
- LLaMa/RWKV onnx models, quantization and testcase☆365Updated 2 years ago
- BladeDISC is an end-to-end DynamIc Shape Compiler project for machine learning workloads.☆889Updated 8 months ago
- export llama to onnx☆132Updated 8 months ago
- fastllm是后端无依赖的高性能大模型推理库。同时支持张量并行推理稠密模型和混合模式推理MOE模型,任意10G以上显卡即可推理满血DeepSeek。双路9004/9005服务器+单显卡部署DeepSeek满血满精度原版模型,单并发20tps;INT4量化模型单并发30tp…☆3,877Updated this week