rebase: align vllm-omni with vLLM ac9126e58aa7

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
This commit is contained in:
tzhouam committed 2026-10-02 10:37:50 +08:00
1 parent 383cc5ef1d
commit 2721f16ca8
93 files changed
+1908 -547

No files matched your search

+28 -2
View File
@@ -1,5 +1,5 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
# SPDX-FileCopyrightText: Copyright contributors to the vLLM-Omni project
"""Regression tests for OmniRequest substitutability with the base Request.
vllm-omni rebinds ``vllm.v1.request.Request`` to ``OmniRequest`` at import
@@ -13,13 +13,16 @@ substitutable with the base class — including base-style calls that pass
import inspect
import msgspec
import numpy as np
import pytest
import torch
from vllm.sampling_params import SamplingParams
from vllm.v1.engine import EngineCoreRequest
from vllm.v1.kv_hints import KvHintAction, KvHintsEnvelope
from vllm.v1.request import Request
from vllm_omni.engine import PromptEmbedsPayload
from vllm_omni.engine import OmniEngineCoreRequest, PromptEmbedsPayload
from vllm_omni.request import OmniRequest, OmniStreamingUpdate
pytestmark = [pytest.mark.core_model, pytest.mark.cpu]
@@ -111,3 +114,26 @@ def test_model_intermediate_buffer_round_trips_to_streaming_update():
assert update is not None
assert request.model_intermediate_buffer is buffer
assert update.model_intermediate_buffer is buffer
def test_kv_hints_survive_omni_upgrade_wire_transport_and_scheduler_conversion():
hints = KvHintsEnvelope("1", "hint-message", [KvHintAction("a", "prefetch", "1", {"blocks": [7]})])
core = EngineCoreRequest(
request_id="hint-request",
prompt_token_ids=[1, 2],
mm_features=None,
sampling_params=SamplingParams(max_tokens=2),
pooling_params=None,
arrival_time=0.0,
lora_request=None,
cache_salt=None,
data_parallel_rank=None,
session_id="session",
kv_hints=hints,
)
upgraded = OmniEngineCoreRequest.from_request(core)
decoded = msgspec.msgpack.decode(msgspec.msgpack.encode(upgraded), type=OmniEngineCoreRequest)
scheduled = OmniRequest.from_engine_core_request(decoded, block_hasher=None)
assert decoded.session_id == "session"
assert scheduled.kv_hints == hints
assert scheduled.session_id == "session"