xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-11 03:45:02 +08:00
Code Issues Packages Projects Releases Wiki Activity

Add runai model streamer e2e test for GCS (#28079)

Browse Source 
Signed-off-by: Alexis MacAskill <amacaskill@google.com>
This commit is contained in:
Alexis MacAskill 2025-11-06 19:07:54 -08:00 committed by GitHub
parent e70fbc599b
commit a47d94f18c
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 20 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
.buildkite/test-pipeline.yaml
View File

@ -546,8 +546,11 @@ steps:
- label: Model Executor Test # 23min - label: Model Executor Test # 23min
timeout_in_minutes: 35 timeout_in_minutes: 35
torch_nightly: true
mirror_hardwares: [amdexperimental] mirror_hardwares: [amdexperimental]
source_file_dependencies: source_file_dependencies:
- vllm/engine/arg_utils.py
- vllm/config/model.py
- vllm/model_executor - vllm/model_executor
- tests/model_executor - tests/model_executor
- tests/entrypoints/openai/test_tensorizer_entrypoint.py - tests/entrypoints/openai/test_tensorizer_entrypoint.py

17
tests/model_executor/model_loader/runai_model_streamer/test_runai_model_streamer_loader.py
View File

@ -1,12 +1,16 @@
# SPDX-License-Identifier: Apache-2.0 # SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project # SPDX-FileCopyrightText: Copyright contributors to the vLLM project
import pytest
from vllm import SamplingParams from vllm import SamplingParams
from vllm.config.load import LoadConfig from vllm.config.load import LoadConfig
from vllm.model_executor.model_loader import get_model_loader from vllm.model_executor.model_loader import get_model_loader
load_format = "runai_streamer" load_format = "runai_streamer"
test_model = "openai-community/gpt2" test_model = "openai-community/gpt2"
# TODO(amacaskill): Replace with a GKE owned GCS bucket.
test_gcs_model = "gs://vertex-model-garden-public-us/codegemma/codegemma-2b/"
prompts = [ prompts = [
"Hello, my name is", "Hello, my name is",
@ -32,3 +36,16 @@ def test_runai_model_loader_download_files(vllm_runner):
with vllm_runner(test_model, load_format=load_format) as llm: with vllm_runner(test_model, load_format=load_format) as llm:
deserialized_outputs = llm.generate(prompts, sampling_params) deserialized_outputs = llm.generate(prompts, sampling_params)
assert deserialized_outputs assert deserialized_outputs
def test_runai_model_loader_download_files_gcs(
vllm_runner, monkeypatch: pytest.MonkeyPatch
):
monkeypatch.setenv("GOOGLE_CLOUD_PROJECT", "fake-project")
monkeypatch.setenv("RUNAI_STREAMER_GCS_USE_ANONYMOUS_CREDENTIALS", "true")
monkeypatch.setenv(
"CLOUD_STORAGE_EMULATOR_ENDPOINT", "https://storage.googleapis.com"
)
with vllm_runner(test_gcs_model, load_format=load_format) as llm:
deserialized_outputs = llm.generate(prompts, sampling_params)
assert deserialized_outputs