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
  ☆746Updated last year
• Ascend / pytorch
  Ascend PyTorch adapter (torch_npu). Mirror of https://gitee.com/ascend/pytorch
  ☆476Updated this week
• MooreThreads / vllm_musa
  A high-throughput and memory-efficient inference and serving engine for LLMs
  ☆73Updated last year
• wangzhaode / llm-export
  llm-export can export llm model to onnx.
  ☆340Updated 2 months ago
• ZRayZzz / flash-attention-v100
  ☆66Updated last year
• PaddlePaddle / PaddleCustomDevice
  PaddlePaddle custom device implementaion. (『飞桨』自定义硬件接入实现)
  ☆101Updated this week
• 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
  ☆489Updated last year
• sophgo / tpu-mlir
  Machine learning compiler based on MLIR for Sophgo TPU.
  ☆839Updated last week
• MooreThreads / mutlass
  MUSA Templates for Linear Algebra Subroutines
  ☆39Updated 3 weeks ago
• mlc-ai / mlc-zh
  ☆623Updated 3 weeks ago
• pigirons / cpufp
  A CPU tool for benchmarking the peak of floating points
  ☆571Updated 3 weeks ago
• flagos-ai / FlagGems
  FlagGems is an operator library for large language models implemented in the Triton Language.
  ☆824Updated this week
• sophgo / LLM-TPU
  Run generative AI models in sophgo BM1684X/BM1688
  ☆260Updated this week
• ModelTC / LightCompress
  [EMNLP 2024 & AAAI 2026] A powerful toolkit for compressing large models including LLMs, VLMs, and video generative models.
  ☆659Updated last month
• QwenLM / qwen.cpp
  C++ implementation of Qwen-LM
  ☆614Updated last year
• MooreThreads / tutorial_on_musa
  ☆43Updated last month
• Cambricon / mlu-ops
  Efficient operation implementation based on the Cambricon Machine Learning Unit (MLU) .
  ☆147Updated 2 weeks ago
• hyperai / triton-cn
  Triton Documentation in Chinese Simplified / Triton 中文文档
  ☆96Updated 3 weeks ago
• Tencent / KsanaLLM
  ☆518Updated this week
• tile-ai / tilelang-ascend
  Ascend TileLang adapter
  ☆177Updated this week
• flagos-ai / FlagScale
  FlagScale is a large model toolkit based on open-sourced projects.
  ☆463Updated this week
• luchangli03 / export_llama_to_onnx
  export llama to onnx
  ☆137Updated last year
• OpenPPL / ppl.llm.serving
  ☆130Updated last year
• bytedance / byteir
  A model compilation solution for various hardware
  ☆458Updated 4 months ago
• pnnx / pnnx
  PyTorch Neural Network eXchange
  ☆665Updated this week
• microsoft / T-MAC
  Low-bit LLM inference on CPU/NPU with lookup table
  ☆906Updated 7 months ago
• bytedance / ByteTransformer
  optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052
  ☆476Updated last year
• intel / xFasterTransformer
  ☆435Updated 3 months ago
• DeepLink-org / dlinfer
  ☆71Updated this week
• sunkx109 / llama.cpp
  llama 2 Inference
  ☆43Updated 2 years ago