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
  ☆738Updated last year
• Ascend / pytorch
  Ascend PyTorch adapter (torch_npu). Mirror of https://gitee.com/ascend/pytorch
  ☆413Updated this week
• MooreThreads / vllm_musa
  A high-throughput and memory-efficient inference and serving engine for LLMs
  ☆56Updated 10 months ago
• sophgo / tpu-mlir
  Machine learning compiler based on MLIR for Sophgo TPU.
  ☆789Updated last week
• MooreThreads / mutlass
  MUSA Templates for Linear Algebra Subroutines
  ☆31Updated 6 months ago
• FlagOpen / FlagGems
  FlagGems is an operator library for large language models implemented in the Triton Language.
  ☆661Updated this week
• PaddlePaddle / PaddleCustomDevice
  PaddlePaddle custom device implementaion. (『飞桨』自定义硬件接入实现)
  ☆94Updated this week
• wangzhaode / llm-export
  llm-export can export llm model to onnx.
  ☆304Updated 7 months ago
• bytedance / ByteTransformer
  optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052
  ☆475Updated last year
• sophgo / LLM-TPU
  Run generative AI models in sophgo BM1684X/BM1688
  ☆236Updated last 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
  ☆487Updated 10 months ago
• mlc-ai / mlc-zh
  ☆615Updated last year
• pigirons / cpufp
  A CPU tool for benchmarking the peak of floating points
  ☆559Updated last month
• hyperai / triton-cn
  Triton Documentation in Chinese Simplified / Triton 中文文档
  ☆80Updated 4 months ago
• QwenLM / qwen.cpp
  C++ implementation of Qwen-LM
  ☆609Updated 8 months ago
• Cambricon / mlu-ops
  Efficient operation implementation based on the Cambricon Machine Learning Unit (MLU) .
  ☆127Updated last week
• ModelTC / LightCompress
  A powerful toolkit for compressing large models including LLM, VLM, and video generation models.
  ☆550Updated last week
• Tencent / KsanaLLM
  ☆485Updated 3 weeks ago
• ZRayZzz / flash-attention-v100
  ☆50Updated last year
• NVIDIA / cudnn-frontend
  cudnn_frontend provides a c++ wrapper for the cudnn backend API and samples on how to use it
  ☆608Updated 2 weeks ago
• pnnx / pnnx
  PyTorch Neural Network eXchange
  ☆618Updated last week
• FlagOpen / FlagScale
  FlagScale is a large model toolkit based on open-sourced projects.
  ☆347Updated this week
• MooreThreads / MobiMaliangSDK
  ☆118Updated last year
• microsoft / T-MAC
  Low-bit LLM inference on CPU/NPU with lookup table
  ☆845Updated 2 months ago
• BBuf / how-to-learn-deep-learning-framework
  how to learn PyTorch and OneFlow
  ☆449Updated last year
• OpenPPL / ppl.nn.llm
  ☆140Updated last year
• tpoisonooo / llama.onnx
  LLaMa/RWKV onnx models, quantization and testcase
  ☆365Updated 2 years ago
• alibaba / BladeDISC
  BladeDISC is an end-to-end DynamIc Shape Compiler project for machine learning workloads.
  ☆889Updated 8 months ago
• luchangli03 / export_llama_to_onnx
  export llama to onnx
  ☆132Updated 8 months ago
• ztxz16 / fastllm
  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