Skip to content
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.

Sign up for GitHub

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

[Frontend] [Neuron] Parse literals out of override-neuron-config #8959

Merged
merged 3 commits into from
Oct 3, 2024
Merged

[Frontend] [Neuron] Parse literals out of override-neuron-config #8959

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
14161b1
Parse literals out of override-neuron-config
Sep 27, 2024
f93ec21
Fix test name
Sep 30, 2024
63dcb6c
Prevent autoformating of test parameters
Oct 3, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
22 changes: 14 additions & 8 deletions tests/engine/test_arg_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,22 +42,28 @@ def test_bad_nullable_kvs(arg):
nullable_kvs(arg)


@pytest.mark.parametrize(("arg", "expected"), [
(None, None),
("{}", {}),
@pytest.mark.parametrize(("arg", "expected", "option"), [
(None, None, "mm-processor-kwargs"),
("{}", {}, "mm-processor-kwargs"),
('{"num_crops": 4}', {
"num_crops": 4
}),
}, "mm-processor-kwargs"),
('{"foo": {"bar": "baz"}}', {
"foo": {
"bar": "baz"
}
}),
}, "mm-processor-kwargs"),
('{"cast_logits_dtype":"bfloat16","sequence_parallel_norm":true,"sequence_parallel_norm_threshold":2048}',
{
"cast_logits_dtype": "bfloat16",
"sequence_parallel_norm": True,
"sequence_parallel_norm_threshold": 2048,
}, "override-neuron-config"),
])
DarkLight1337 marked this conversation as resolved.
Show resolved Hide resolved
def test_mm_processor_kwargs_prompt_parser(arg, expected):
def test_composite_arg_parser(arg, expected, option):
parser = EngineArgs.add_cli_args(FlexibleArgumentParser())
if arg is None:
args = parser.parse_args([])
else:
args = parser.parse_args(["--mm-processor-kwargs", arg])
assert args.mm_processor_kwargs == expected
args = parser.parse_args([f"--{option}", arg])
assert getattr(args, option.replace("-", "_")) == expected
9 changes: 3 additions & 6 deletions vllm/engine/arg_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -789,13 +789,10 @@ def add_cli_args(parser: FlexibleArgumentParser) -> FlexibleArgumentParser:
"lower performance.")
parser.add_argument(
'--override-neuron-config',
type=lambda configs: {
str(key): value
for key, value in
(config.split(':') for config in configs.split(','))
},
type=json.loads,
default=None,
help="override or set neuron device configuration.")
help="Override or set neuron device configuration. "
"e.g. {\"cast_logits_dtype\": \"bloat16\"}.'")

return parser

Expand Down
Loading