Alternatives and similar repositories for zero-copy-model-loading:

Users that are interested in zero-copy-model-loading are comparing it to the libraries listed below

• bentoml / simple_di
  Simple dependency injection framework for Python
  ☆20Updated 8 months ago
• alvarobartt / safejax
  Serialize JAX, Flax, Haiku, or Objax model params with 🤗`safetensors`
  ☆43Updated 8 months ago
• pytorch-labs / torchfix
  TorchFix - a linter for PyTorch-using code with autofix support
  ☆122Updated 3 weeks ago
• bentoml / IF-multi-GPUs-demo
  ☆12Updated last year
• pytorch / torchsnapshot
  A performant, memory-efficient checkpointing library for PyTorch applications, designed with large, complex distributed workloads in mind…
  ☆153Updated last month
• jax-ml / ml_dtypes
  A stand-alone implementation of several NumPy dtype extensions used in machine learning.
  ☆240Updated this week
• octoml / octoml-profile
  Home for OctoML PyTorch Profiler
  ☆107Updated last year
• coreweave / tensorizer
  Module, Model, and Tensor Serialization/Deserialization
  ☆210Updated 2 months ago
• google / jaxonnxruntime
  A user-friendly tool chain that enables the seamless execution of ONNX models using JAX as the backend.
  ☆106Updated this week
• graphcore-research / out-of-the-box-fp8-training
  Demo of the unit_scaling library, showing how a model can be easily adapted to train in FP8.
  ☆43Updated 6 months ago
• ezyang / torchdbg
  PyTorch centric eager mode debugger
  ☆44Updated last month
• sdpython / mlprodict
  Productionize machine learning predictions, with ONNX or without
  ☆65Updated last year
• JiahaoYao / awesome-ray
  Ray - A curated list of resources: https://github.com/ray-project/ray
  ☆48Updated this week
• NVIDIA / free-threaded-python
  No-GIL Python environment featuring NVIDIA Deep Learning libraries.
  ☆41Updated 2 months ago
• pytorch / torchdistx
  Torch Distributed Experimental
  ☆115Updated 5 months ago
• hora-search / horapy
  🐍 Python bidding for the Hora Approximate Nearest Neighbor Search Algorithm library
  ☆68Updated 3 years ago
• hamelsmu / llama-inference
  experiments with inference on llama
  ☆104Updated 7 months ago
• neuralmagic / compressed-tensors
  A safetensors extension to efficiently store sparse quantized tensors on disk
  ☆66Updated this week
• aredden / torch-cublas-hgemm
  PyTorch half precision gemm lib w/ fused optional bias + optional relu/gelu
  ☆48Updated last month
• ryantd / veloce
  WIP. Veloce is a low-code Ray-based parallelization library that makes machine learning computation novel, efficient, and heterogeneous.
  ☆18Updated 2 years ago
• tensorchord / inference-benchmark
  Benchmark for machine learning model online serving (LLM, embedding, Stable-Diffusion, Whisper)
  ☆28Updated last year
• Lightning-Universe / Training-Studio_app
  Lightning HPO & Training Studio App
  ☆18Updated last year
• fidelity / stoke
  A lightweight wrapper for PyTorch that provides a simple declarative API for context switching between devices, distributed modes, mixed-…
  ☆66Updated last year
• UmerHA / triton_util
  Make triton easier
  ☆44Updated 7 months ago
• pytorch / multipy
  torch::deploy (multipy for non-torch uses) is a system that lets you get around the GIL problem by running multiple Python interpreters i…
  ☆178Updated last month
• lianakoleva / no-libtorch-compile
  ☆21Updated 3 months ago
• triton-inference-server / pytorch_backend
  The Triton backend for the PyTorch TorchScript models.
  ☆141Updated last week
• kshitij12345 / torchnnprofiler
  Context Manager to profile the forward and backward times of PyTorch's nn.Module
  ☆84Updated last year
• lernapparat / torchhacks
  Hacks for PyTorch
  ☆18Updated last year
• zhisbug / ray-scalable-ml-design
  Some microbenchmarks and design docs before commencement
  ☆12Updated 3 years ago