Alternatives and similar repositories for torch_musa:

Users that are interested in torch_musa are comparing it to the libraries listed below

• MegEngine / InferLLM
  a lightweight LLM model inference framework
  ☆713Updated 9 months ago
• Ascend / pytorch
  Ascend PyTorch adapter (torch_npu). Mirror of https://gitee.com/ascend/pytorch
  ☆294Updated this week
• PaddlePaddle / PaddleCustomDevice
  PaddlePaddle custom device implementaion. (『飞桨』自定义硬件接入实现)
  ☆78Updated last week
• MooreThreads / MobiMaliangSDK
  ☆119Updated last year
• wangzhaode / llm-export
  llm-export can export llm model to onnx.
  ☆257Updated last week
• sophgo / tpu-mlir
  Machine learning compiler based on MLIR for Sophgo TPU.
  ☆649Updated last week
• modelscope / dash-infer
  DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including …
  ☆220Updated this week
• QwenLM / qwen.cpp
  C++ implementation of Qwen-LM
  ☆571Updated last month
• luchangli03 / export_llama_to_onnx
  export llama to onnx
  ☆112Updated last month
• OpenPPL / ppl.nn.llm
  ☆140Updated 9 months ago
• hyperai / triton-cn
  Triton Documentation in Chinese Simplified / Triton 中文文档
  ☆52Updated 2 weeks ago
• FlagOpen / FlagGems
  FlagGems is an operator library for large language models implemented in Triton Language.
  ☆407Updated this week
• MooreThreads / vllm_musa
  A high-throughput and memory-efficient inference and serving engine for LLMs
  ☆37Updated 3 months ago
• mlc-ai / mlc-zh
  ☆598Updated 7 months ago
• OpenPPL / ppl.llm.serving
  ☆127Updated last month
• bytedance / ByteTransformer
  optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052
  ☆469Updated 10 months ago
• sophgo / LLM-TPU
  Run generative AI models in sophgo BM1684X
  ☆155Updated this week
• ifromeast / cuda_learning
  learning how CUDA works
  ☆190Updated 5 months ago
• MegEngine / MegCC
  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
  ☆476Updated 3 months ago
• sophgo / ChatGLM2-TPU
  run ChatGLM2-6B in BM1684X
  ☆49Updated 10 months ago
• FlagOpen / FlagScale
  FlagScale is a large model toolkit based on open-sourced projects.
  ☆209Updated this week
• mindspore-lab / mindformers
  ☆151Updated last month
• XiaoMi / StableDiffusionOnDevice
  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。
  ☆135Updated 10 months ago
• Ascend / AscendSpeed
  ☆76Updated last year
• Cambricon / mlu-ops
  Efficient operation implementation based on the Cambricon Machine Learning Unit (MLU) .
  ☆108Updated last week
• Oneflow-Inc / libai
  LiBai(李白): A Toolbox for Large-Scale Distributed Parallel Training
  ☆398Updated last week
• alibaba / rtp-llm
  RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.
  ☆607Updated last week
• CalvinXKY / BasicCUDA
  A tutorial for CUDA&PyTorch
  ☆126Updated last week
• pcg-mlp / KsanaLLM
  ☆311Updated last week
• ModelTC / llmc
  [EMNLP 2024 Industry Track] This is the official PyTorch implementation of "LLMC: Benchmarking Large Language Model Quantization with a V…
  ☆390Updated last week