Alternatives and similar repositories for models:

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

• Ascend / AscendSpeed
  ☆76Updated last year
• Oneflow-Inc / libai
  LiBai(李白): A Toolbox for Large-Scale Distributed Parallel Training
  ☆397Updated 2 months ago
• YellowOldOdd / SDBI
  Simple Dynamic Batching Inference
  ☆145Updated 2 years ago
• Oneflow-Inc / oneflow-documentation
  oneflow documentation
  ☆68Updated 6 months ago
• volcengine / veGiantModel
  ☆211Updated last year
• void-main / FasterTransformer
  Transformer related optimization, including BERT, GPT
  ☆61Updated last year
• Oneflow-Inc / OneFlow-Benchmark
  OneFlow models for benchmarking.
  ☆105Updated 5 months ago
• OpenPPL / ppl.llm.serving
  ☆127Updated 3 weeks ago
• OpenPPL / ppl.nn.llm
  ☆140Updated 8 months ago
• Rayrtfr / FasterTransformer
  Transformer related optimization, including BERT, GPT
  ☆17Updated last year
• THUDM / FasterTransformer
  Transformer related optimization, including BERT, GPT
  ☆39Updated last year
• luchangli03 / export_llama_to_onnx
  export llama to onnx
  ☆111Updated 3 weeks ago
• luchangli03 / onnxsim_large_model
  simplify >2GB large onnx model
  ☆51Updated last month
• Oneflow-Inc / oneflow_convert
  OneFlow->ONNX
  ☆42Updated last year
• FlagOpen / FlagAttention
  A collection of memory efficient attention operators implemented in the Triton language.
  ☆229Updated 7 months ago
• openmlsys / openmlsys-cuda
  Tutorials for writing high-performance GPU operators in AI frameworks.
  ☆126Updated last year
• alibaba / EasyParallelLibrary
  Easy Parallel Library (EPL) is a general and efficient deep learning framework for distributed model training.
  ☆266Updated last year
• AyakaGEMM / Hands-on-GEMM
  ☆105Updated 10 months ago
• Oneflow-Inc / vision
  Datasets, Transforms and Models specific to Computer Vision
  ☆84Updated last year
• zms1999 / SmartMoE
  A MoE impl for PyTorch, [ATC'23] SmartMoE
  ☆60Updated last year
• kwai / Megatron-Kwai
  [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…
  ☆47Updated 5 months ago
• FlagOpen / FlagScale
  FlagScale is a large model toolkit based on open-sourced projects.
  ☆207Updated this week
• Oneflow-Inc / DLPerf
  DeepLearning Framework Performance Profiling Toolkit
  ☆281Updated 2 years ago
• bytedance / decoupleQ
  A quantization algorithm for LLM
  ☆108Updated 6 months ago
• cauyxy / bilivideos
  ☆52Updated last year
• bytedance / ByteTransformer
  optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052
  ☆467Updated 10 months ago
• fanshiqing / grouped_gemm
  PyTorch bindings for CUTLASS grouped GEMM.
  ☆84Updated 2 weeks ago
• torchpipe / torchpipe
  Serving Inside Pytorch
  ☆150Updated 3 weeks ago
• Tlntin / ChatGLM2-6B-TensorRT
  ☆90Updated last year
• madsys-dev / deepseekv2-profile
  ☆71Updated 5 months ago