Remove all references to yapf as it's no longer used (#26251)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
@@ -107,10 +107,8 @@ class EPTestSettings:
|
||||
# NOTE: You can adjust tp_base locally to fit the model in GPU
|
||||
# The values displayed here are only a rough indicator of the size of the model
|
||||
|
||||
# yapf: disable
|
||||
TEST_MODELS = {
|
||||
"deepseek-ai/DeepSeek-V2-Lite-Chat": EPTestSettings.fast(
|
||||
trust_remote_code=True),
|
||||
"deepseek-ai/DeepSeek-V2-Lite-Chat": EPTestSettings.fast(trust_remote_code=True),
|
||||
"mistralai/Mixtral-8x7B-Instruct-v0.1": EPTestSettings.fast(tp_base=4),
|
||||
}
|
||||
|
||||
@@ -192,22 +190,24 @@ def _compare_tp(
|
||||
]
|
||||
|
||||
try:
|
||||
compare_two_settings(model_name,
|
||||
ep_args,
|
||||
tp_args,
|
||||
ep_env,
|
||||
tp_env,
|
||||
method=method,
|
||||
max_wait_seconds=360)
|
||||
compare_two_settings(
|
||||
model_name,
|
||||
ep_args,
|
||||
tp_args,
|
||||
ep_env,
|
||||
tp_env,
|
||||
method=method,
|
||||
max_wait_seconds=360,
|
||||
)
|
||||
except Exception:
|
||||
raise
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
("model_name", "parallel_setup", "distributed_backend", "runner",
|
||||
"test_options"),
|
||||
("model_name", "parallel_setup", "distributed_backend", "runner", "test_options"),
|
||||
[
|
||||
params for model_name, settings in TEST_MODELS.items()
|
||||
params
|
||||
for model_name, settings in TEST_MODELS.items()
|
||||
for params in settings.iter_params(model_name)
|
||||
],
|
||||
)
|
||||
@@ -220,10 +220,12 @@ def test_ep(
|
||||
test_options: EPTestOptions,
|
||||
num_gpus_available,
|
||||
):
|
||||
_compare_tp(model_name,
|
||||
parallel_setup,
|
||||
distributed_backend,
|
||||
runner,
|
||||
test_options,
|
||||
num_gpus_available,
|
||||
method="generate")
|
||||
_compare_tp(
|
||||
model_name,
|
||||
parallel_setup,
|
||||
distributed_backend,
|
||||
runner,
|
||||
test_options,
|
||||
num_gpus_available,
|
||||
method="generate",
|
||||
)
|
||||
|
||||
@@ -100,7 +100,6 @@ class PPTestSettings:
|
||||
# NOTE: You can adjust tp_base and/or pp_base locally to fit the model in GPU
|
||||
# The values displayed here are only a rough indicator of the size of the model
|
||||
|
||||
# yapf: disable
|
||||
TEXT_GENERATION_MODELS = {
|
||||
# [Decoder-only]
|
||||
# Uses Llama
|
||||
@@ -150,7 +149,9 @@ TEXT_GENERATION_MODELS = {
|
||||
"adept/persimmon-8b-chat": PPTestSettings.fast(),
|
||||
"microsoft/phi-2": PPTestSettings.fast(),
|
||||
"microsoft/Phi-3-small-8k-instruct": PPTestSettings.fast(),
|
||||
"microsoft/Phi-3.5-MoE-instruct": PPTestSettings.detailed(multi_node_only=True, load_format="dummy"), # noqa: E501
|
||||
"microsoft/Phi-3.5-MoE-instruct": PPTestSettings.detailed(
|
||||
multi_node_only=True, load_format="dummy"
|
||||
), # noqa: E501
|
||||
"Qwen/Qwen-7B-Chat": PPTestSettings.fast(),
|
||||
"Qwen/Qwen2.5-0.5B-Instruct": PPTestSettings.fast(),
|
||||
"Qwen/Qwen1.5-MoE-A2.7B-Chat": PPTestSettings.fast(),
|
||||
@@ -196,7 +197,6 @@ MULTIMODAL_MODELS = {
|
||||
"Qwen/Qwen2-VL-2B-Instruct": PPTestSettings.fast(),
|
||||
"fixie-ai/ultravox-v0_5-llama-3_2-1b": PPTestSettings.fast(),
|
||||
}
|
||||
# yapf: enable
|
||||
|
||||
# NOTE: You can update this on your local machine to run specific tests
|
||||
TEST_MODELS = [
|
||||
|
||||
Reference in New Issue
Block a user