[V0 Deprecation] Remove LLMEngine (#25033)
Signed-off-by: Woosuk Kwon <woosuk@thinkingmachines.ai> Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
This commit is contained in:
@@ -10,13 +10,6 @@ from transformers import AutoModelForSeq2SeqLM
|
||||
|
||||
from vllm.assets.audio import AudioAsset
|
||||
|
||||
|
||||
@pytest.fixture(autouse=True)
|
||||
def v1(run_with_both_engines):
|
||||
"""We can run both engines for this test."""
|
||||
pass
|
||||
|
||||
|
||||
# FIXME(zhuohan): The test can not pass if we:
|
||||
# 1. Increase max_tokens to 256.
|
||||
# 2. Increase beam_width to 8.
|
||||
|
||||
@@ -9,13 +9,6 @@ import pytest
|
||||
|
||||
from vllm import SamplingParams
|
||||
|
||||
|
||||
@pytest.fixture(autouse=True)
|
||||
def v1(run_with_both_engines):
|
||||
"""We can run both engines for this test."""
|
||||
pass
|
||||
|
||||
|
||||
# We also test with llama because it has generation_config to specify EOS
|
||||
# (past regression).
|
||||
MODELS = ["distilbert/distilgpt2", "meta-llama/Llama-3.2-1B"]
|
||||
|
||||
@@ -8,12 +8,6 @@ from vllm import SamplingParams
|
||||
MODELS = ["distilbert/distilgpt2"]
|
||||
|
||||
|
||||
@pytest.fixture(autouse=True)
|
||||
def v1(run_with_both_engines):
|
||||
"""We can run both engines for this test."""
|
||||
pass
|
||||
|
||||
|
||||
@pytest.mark.parametrize("model", MODELS)
|
||||
@pytest.mark.parametrize("dtype", ["half"])
|
||||
def test_ranks(
|
||||
|
||||
Reference in New Issue
Block a user