[Deprecation][2/N] Replace --task with --runner and --convert (#21470)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Cyrus Leung
2025-07-28 10:42:40 +08:00
committed by GitHub
parent 8f605ee309
commit 86ae693f20
94 changed files with 1117 additions and 1083 deletions

View File

@@ -33,6 +33,10 @@ def check_implementation(
args = (example_prompts, max_tokens, num_logprobs)
with runner_test(model, **kwargs_test, **kwargs) as model_test:
model_config = model_test.llm.llm_engine.model_config
assert model_config.architecture == (
model_config._get_transformers_backend_cls())
outputs_test = model_test.generate_greedy_logprobs(*args)
with runner_ref(model, **kwargs_ref) as model_ref:
@@ -130,8 +134,13 @@ def test_quantization(
model_impl="transformers",
enforce_eager=True,
**quantization_kwargs) as vllm_model: # type: ignore[arg-type]
model_config = vllm_model.llm.llm_engine.model_config
assert model_config.architecture == (
model_config._get_transformers_backend_cls())
transformers_outputs = vllm_model.generate_greedy_logprobs(
example_prompts, max_tokens=max_tokens, num_logprobs=num_logprobs)
check_logprobs_close(
outputs_0_lst=transformers_outputs,
outputs_1_lst=vllm_outputs,
@@ -151,7 +160,6 @@ def test_classify(
example_prompts,
model: str,
dtype: str,
monkeypatch,
) -> None:
import torch
from transformers import AutoModelForSequenceClassification
@@ -160,6 +168,10 @@ def test_classify(
max_model_len=512,
dtype=dtype,
model_impl="transformers") as vllm_model:
model_config = vllm_model.llm.llm_engine.model_config
assert model_config.architecture == (
model_config._get_transformers_backend_cls())
vllm_outputs = vllm_model.classify(example_prompts)
with hf_runner(model,