[misc] Layerwise profile updates (#10242)

Signed-off-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
This commit is contained in:
Varun Sundar Rabindranath
2024-12-16 13:14:57 -05:00
committed by GitHub
parent 2ca830dbaa
commit efbce85f4d
5 changed files with 314 additions and 47 deletions

View File

@@ -201,7 +201,7 @@ steps:
- python3 offline_inference_classification.py
- python3 offline_inference_embedding.py
- python3 offline_inference_scoring.py
- python3 offline_profile.py --model facebook/opt-125m
- python3 offline_profile.py --model facebook/opt-125m run_num_steps --num-steps 2
- label: Prefix Caching Test # 9min
mirror_hardwares: [amd]