search

ThanatosShinji / onnx-tool

A parser, editor and profiler tool for ONNX models.
https://pypi.org/project/onnx-tool/
MIT License
383 stars 51 forks source link

Support accurate LLM profiling and projection #93

Closed luoyu-intel closed 5 days ago

luoyu-intel commented 5 days ago
  1. Add per-node latency projection.
  2. Add multi devices latency projection.
  3. Add model: llama2_7b
  4. Add two devices: Intel Gaudi2H and NV H20