Alternatives and similar repositories for onnx-safetensors:

Users that are interested in onnx-safetensors are comparing it to the libraries listed below

• onnx / neural-compressor
  Model compression for ONNX
  ☆88Updated 4 months ago
• abetlen / ggml-python
  Python bindings for ggml
  ☆140Updated 7 months ago
• inisis / OnnxSlim
  A Toolkit to Help Optimize Onnx Model
  ☆129Updated this week
• onnx / turnkeyml
  LLM SDK for OnnxRuntime GenAI (OGA)
  ☆119Updated this week
• microsoft / onnxscript
  ONNX Script enables developers to naturally author ONNX functions and models using a subset of Python.
  ☆329Updated this week
• microsoft / onnxconverter-common
  Common utilities for ONNX converters
  ☆261Updated 4 months ago
• aredden / torch-cublas-hgemm
  PyTorch half precision gemm lib w/ fused optional bias + optional relu/gelu
  ☆57Updated 4 months ago
• triton-inference-server / tensorrt_backend
  The Triton backend for TensorRT.
  ☆70Updated 3 weeks ago
• neuralmagic / compressed-tensors
  A safetensors extension to efficiently store sparse quantized tensors on disk
  ☆92Updated this week
• neuralmagic / nm-vllm
  A high-throughput and memory-efficient inference and serving engine for LLMs
  ☆262Updated 5 months ago
• microsoft / onnxruntime-extensions
  onnxruntime-extensions: A specialized pre- and post- processing library for ONNX Runtime
  ☆371Updated this week
• huggingface / optimum-amd
  AMD related optimizations for transformer models
  ☆72Updated 4 months ago
• wejoncy / QLLM
  A general 2-8 bits quantization toolbox with GPTQ/AWQ/HQQ/VPTQ, and export to onnx/onnx-runtime easily.
  ☆165Updated 3 weeks ago
• triton-inference-server / onnxruntime_backend
  The Triton backend for the ONNX Runtime.
  ☆140Updated 2 weeks ago
• daquexian / faster-rwkv
  ☆124Updated last year
• huggingface / kernels
  Load compute kernels from the Hub
  ☆107Updated last week
• onnx / steering-committee
  Notes and artifacts from the ONNX steering committee
  ☆25Updated this week
• Repeerc / flash-attention-v2-RDNA3-minimal
  a simple Flash Attention v2 implementation with ROCM (RDNA3 GPU, roc wmma), mainly used for stable diffusion(ComfyUI) in Windows ZLUDA en…
  ☆37Updated 7 months ago
• deepspeedai / DeepSpeed-Kernels
  ☆63Updated last week
• coreweave / tensorizer
  Module, Model, and Tensor Serialization/Deserialization
  ☆220Updated last month
• run-ai / runai-model-streamer
  ☆176Updated this week
• pytorch-labs / triton-cpu
  An experimental CPU backend for Triton (https//github.com/openai/triton)
  ☆40Updated 2 weeks ago
• huggingface / kernel-builder
  👷 Build compute kernels
  ☆24Updated this week
• microsoft / onnxruntime-genai
  Generative AI extensions for onnxruntime
  ☆667Updated this week
• WaveSpeedAI / QuantumAttention
  [WIP] Better (FP8) attention for Hopper
  ☆26Updated last month
• chengzeyi / piflux
  (WIP) Parallel inference for black-forest-labs' FLUX model.
  ☆18Updated 4 months ago
• mag- / gpu_benchmark
  Gpu benchmark
  ☆57Updated 2 months ago
• EmbeddedLLM / vllm
  vLLM: A high-throughput and memory-efficient inference and serving engine for LLMs
  ☆87Updated this week
• 99991 / pygguf
  GGUF parser in Python
  ☆26Updated 7 months ago
• mobiusml / gemlite
  Fast low-bit matmul kernels in Triton
  ☆275Updated this week