feat(frontend): session id plumbing into requests (#48048)
Signed-off-by: Karen Chung <karenc@nvidia.com>
This commit is contained in:
@@ -1,6 +1,9 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
from vllm.v1.request import RequestStatus
|
||||
|
||||
from vllm import SamplingParams
|
||||
from vllm.v1.engine import EngineCoreRequest
|
||||
from vllm.v1.request import Request, RequestStatus
|
||||
|
||||
|
||||
def test_request_status_fmt_str():
|
||||
@@ -18,3 +21,22 @@ def test_request_status_fmt_str():
|
||||
assert f"{RequestStatus.FINISHED_LENGTH_CAPPED}" == "FINISHED_LENGTH_CAPPED"
|
||||
assert f"{RequestStatus.FINISHED_ABORTED}" == "FINISHED_ABORTED"
|
||||
assert f"{RequestStatus.FINISHED_IGNORED}" == "FINISHED_IGNORED"
|
||||
|
||||
|
||||
def test_request_copies_session_id_from_engine_core_request():
|
||||
engine_request = EngineCoreRequest(
|
||||
request_id="request-1",
|
||||
prompt_token_ids=[1, 2, 3],
|
||||
mm_features=None,
|
||||
sampling_params=SamplingParams(max_tokens=1),
|
||||
pooling_params=None,
|
||||
arrival_time=0.0,
|
||||
lora_request=None,
|
||||
cache_salt=None,
|
||||
data_parallel_rank=None,
|
||||
session_id="session-1",
|
||||
)
|
||||
|
||||
request = Request.from_engine_core_request(engine_request, block_hasher=None)
|
||||
|
||||
assert request.session_id == "session-1"
|
||||
|
||||
Reference in New Issue
Block a user