[CI] Organize speculative decoding E2E tests by coverage (#50330)
Signed-off-by: mgoin <mgoin64@gmail.com> Signed-off-by: Michael Goin <mgoin64@gmail.com> Co-authored-by: OpenAI Codex <noreply@openai.com> Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
This commit is contained in:
co-authored by
OpenAI Codex
mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
parent
b40d859c7b
commit
fcdc7c2e9c
@@ -0,0 +1,25 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
|
||||
import pytest
|
||||
import torch
|
||||
|
||||
from vllm import SamplingParams
|
||||
|
||||
from .utils import greedy_sampling
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def sampling_config() -> SamplingParams:
|
||||
return greedy_sampling()
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def model_name() -> str:
|
||||
return "meta-llama/Llama-3.1-8B-Instruct"
|
||||
|
||||
|
||||
@pytest.fixture(autouse=True)
|
||||
def reset_torch_dynamo():
|
||||
yield
|
||||
torch._dynamo.reset()
|
||||
Reference in New Issue
Block a user