[Bugfix][MRV2] Keep input_ids on later PP stages for raw-token models (#61016)

Signed-off-by: booth-algo <kevinlauofficial01@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Kevin H. Luu <khluu000@gmail.com>
This commit is contained in:
Kevin
2026-10-15 12:54:21 -07:00
committed by GitHub
co-authored by Claude Opus 5.5 Kevin H. Luu
parent d486219fc2
commit d12ea8e309
6 changed files with 51 additions and 5 deletions
+18
View File
@@ -1,6 +1,10 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
import json
import pytest
from tests.plugins_tests.test_oot_registration_online import (
run_and_test_dummy_opt_api_server,
)
@@ -8,3 +12,17 @@ from tests.plugins_tests.test_oot_registration_online import (
def test_distributed_oot(dummy_opt_path: str):
run_and_test_dummy_opt_api_server(dummy_opt_path, tp=2)
@pytest.mark.parametrize("enforce_eager", [True, False])
def test_distributed_oot_pp_raw_input_tokens(dummy_opt_path: str, enforce_eager: bool):
# The model asserts that input_ids reaches every pipeline stage.
overrides = {"architectures": ["MyOPTRawInputTokensForCausalLM"]}
extra_args = ["-pp", "2", "--hf-overrides", json.dumps(overrides)]
if enforce_eager:
extra_args.append("--enforce-eager")
run_and_test_dummy_opt_api_server(
dummy_opt_path,
extra_args=extra_args,
env_dict={"VLLM_USE_V2_MODEL_RUNNER": "1"},
)