-
Notifications
You must be signed in to change notification settings - Fork 311
[Userbenchmark] Add configuration support for test_bench
#2592
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
base: main
Are you sure you want to change the base?
Conversation
userbenchmark/test_bench/run.py
Outdated
model_set = set(list_models(internal=False)) | ||
device = config_obj["device"] | ||
configs = [] | ||
for model in model_set: | ||
cfg = next(filter(lambda c: c["model"] == model, config_obj["models"]), None) | ||
tests = cfg.get("tests", "eval") if cfg is not None else ["eval"] | ||
for test in tests: | ||
config = TorchBenchModelConfig( | ||
name=model, | ||
device=device, | ||
test=test, | ||
batch_size=cfg.get("batch_size", None) if cfg is not None else None, | ||
extra_args=[], | ||
skip=cfg is not None and cfg.get("skip", False), | ||
) | ||
print(config) | ||
configs.append(config) | ||
return configs |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This means that we always list all models and apply configuration on them.
@xuzhao9 Could you please help review this? Any comments are welcome! |
Hi @xuzhao9, just a gentle reminder to check this PR when you get a chance. Thanks! |
Hi @xuzhao9, could you please help review this?. Thanks for your time! |
fixes: #2590
Configuration file might like this: