xla

3ccb4ed2 - benchmarks/torchbench_model: skip benchmarks that fail to load (#6199)

benchmarks/torchbench_model: skip benchmarks that fail to load (#6199) In "dfcf306e7 Apply precision config env vars in the root process. (#6152)" we started running load_benchmark() from experiment_runner's main process. Unfortunately, load_benchmark() for some models does exit the calling process, which results in experiment_runner exiting prematurely. Work around this issue by adding these models to the deny list, so that experiment_runner does not die early.