Files
pytorch/benchmarks/dynamo/timm_models.yaml
Boyuan Feng 83458197d1 [Benchmark] remove old timm models from benchmark (#164805)
Prune models from TorchInductor dashboard to reduce ci cost. This PR prunes for timm models according to the [doc](https://docs.google.com/document/d/1nLPNNAU-_M9Clx9FMrJ1ycdPxe-xRA54olPnsFzdpoU/edit?tab=t.0), which reduces from 60 to 14 models.

Pull Request resolved: https://github.com/pytorch/pytorch/pull/164805
Approved by: https://github.com/anijain2305, https://github.com/seemethere, https://github.com/huydhn, https://github.com/malfet
2025-10-08 17:14:58 +00:00

14 lines
292 B
YAML

# removing this file prevents the TimmRunner from dynamically skipping models
skip:
all:
- ~
device:
cpu:
- ~
# Skip these additional models when running on aarch64
cpu_aarch64:
# timeout on aarch64
- dm_nfnet_f0
- nfnet_l0
- visformer_small