How does torch.compile() achieve massive speedups despite highly optimized NumPy functions? See how operator fusion works! ⚡
-
Updated
Aug 3, 2026 - Jupyter Notebook
#
operator-fusion
Here are 7 public repositories matching this topic...
面向 Transformer 推理学习的精简 Triton 算子：RMSNorm+RoPE、Gated MLP、FlashAttention
python acceleration deep-learning high-performance cuda inference pytorch nvidia triton gpu-computing quantization gpu-kernels kernel-fusion llm fp8 rotary-position-embedding rmsnorm llm-inference operator-fusion transformer-inference
-
Updated
Aug 6, 2026 - Python
A specialized compiler that optimizes deep learning models for AI accelerators with operator fusion, memory optimization, and hardware-specific passes.
-
Updated
Mar 1, 2026 - Python
C++17 ONNX inference optimizer + CPU runtime for Apple Silicon. Operator fusion via IR passes, Accelerate AMX-backed sgemm; benched vs ONNX Runtime CPU EP on DistilBERT (1.26x baseline speedup, 6.99x ORT on raw MatMul).
machine-learning protobuf compiler cpp transformer accelerate cpp17 amx inference-engine sgemm ml-infrastructure onnx gelu distilbert apple-silicon operator-fusion
-
Updated
Jul 9, 2026 - C++
TensorMorph is an AI-assisted MLIR compiler for TOSA graph optimization and operator fusion.
compiler graph-optimization mlir operator-fusion ml-compiler tosa tensor-optimization ai-assisted-compilation
-
Updated
Jan 12, 2026 - C++
From-scratch C++ inference compiler: ONNX parsing, operator fusion, and handwritten NCHW kernels that match ONNX Runtime exactly on a trained MNIST CNN.
-
Updated
Jul 8, 2026 - C++
Native Rust edge inference engine with zero-copy memmap2 tensor loading, register-fused Linear+ReLU kernels, and scenario-aware MoE routing via rayon work-stealing — achieving 352µs lightweight and 1.39ms dense expert execution.
rust high-performance zero-copy parallel-computing systems-programming inference-engine edge-computing memory-mapping mixture-of-experts operator-fusion
-
Updated
May 31, 2026 - Rust
Improve this page
Add a description, image, and links to the operator-fusion topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the operator-fusion topic, visit your repo's landing page and select "manage topics."