onnx / ir-pyLinks
Efficient in-memory representation for ONNX, in Python
☆32Updated last week
Alternatives and similar repositories for ir-py
Users that are interested in ir-py are comparing it to the libraries listed below
Sorting:
- TORCH_LOGS parser for PT2☆64Updated last week
- Home for OctoML PyTorch Profiler☆114Updated 2 years ago
- An experimental CPU backend for Triton (https//github.com/openai/triton)☆47Updated 3 months ago
- Notes and artifacts from the ONNX steering committee☆27Updated 2 weeks ago
- ☆218Updated 10 months ago
- ☆21Updated 8 months ago
- 🏙 Interactive performance profiling and debugging tool for PyTorch neural networks.☆64Updated 10 months ago
- High-Performance SGEMM on CUDA devices☆112Updated 10 months ago
- Framework to reduce autotune overhead to zero for well known deployments.☆85Updated 2 months ago
- MLIR-based partitioning system☆148Updated this week
- ☆71Updated 7 months ago
- ONNX Script enables developers to naturally author ONNX functions and models using a subset of Python.☆409Updated this week
- Model compression for ONNX☆99Updated last year
- extensible collectives library in triton☆91Updated 7 months ago
- TritonParse: A Compiler Tracer, Visualizer, and Reproducer for Triton Kernels☆171Updated last week
- Explore training for quantized models☆25Updated 4 months ago
- Repository for CPU Kernel Generation for LLM Inference☆27Updated 2 years ago
- ☆51Updated this week
- A safetensors extension to efficiently store sparse quantized tensors on disk☆210Updated this week
- ☆93Updated last year
- Memory Optimizations for Deep Learning (ICML 2023)☆110Updated last year
- Ahead of Time (AOT) Triton Math Library☆84Updated last week
- Machine Learning Agility (MLAgility) benchmark and benchmarking tools☆40Updated 3 months ago
- PyTorch centric eager mode debugger☆48Updated 11 months ago
- How to ensure correctness and ship LLM generated kernels in PyTorch☆121Updated last week
- Visualize ONNX models with model-explorer☆63Updated last month
- MLPerf™ logging library☆37Updated last month
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆122Updated last year
- A stand-alone implementation of several NumPy dtype extensions used in machine learning.☆308Updated this week
- A performant, memory-efficient checkpointing library for PyTorch applications, designed with large, complex distributed workloads in mind…☆161Updated 2 months ago