[Rebase] Rebase to vllm 0.26.0 (#5443)

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Signed-off-by: tzhouam <tzhouam@gmail.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: tzhouam <tzhouam@gmail.com>
This commit is contained in:
authored and GitHub committed 2026-07-27 23:35:49 +08:00
1 parent fb89ab43ea
commit cbab1d4d8f
41 files changed
+334 -183

No files matched your search

+3
View File
@@ -69,6 +69,9 @@ def test_speech_extra_params_reach_model_sampler_as_sampling_metadata(monkeypatc
vocab_size=1024,
block_sizes=[1],
kernel_block_sizes=[1],
# vLLM 0.26: one entry per KV cache group; max_model_len=8 with
# block_sizes=[1] means one group of 8 blocks.
max_num_blocks_per_req=[8],
)
input_batch.add_request(
CachedRequestState(
@@ -4,7 +4,7 @@ from types import SimpleNamespace
import pytest
import torch
from vllm.config import CacheConfig
from vllm.v1.worker.gpu_model_runner import EMPTY_MODEL_RUNNER_OUTPUT
from vllm.v1.outputs import EMPTY_MODEL_RUNNER_OUTPUT
import vllm_omni.worker.gpu_generation_model_runner as gen_runner_module
from vllm_omni.worker.gpu_generation_model_runner import (
+1 -1
View File
@@ -1245,7 +1245,7 @@ class TestRankAwareKVRouting(unittest.TestCase):
class TestAttachOmniConnectorOutput(unittest.TestCase):
def test_wraps_empty_model_runner_output_when_signals_exist(self):
from vllm.v1.worker.gpu_model_runner import EMPTY_MODEL_RUNNER_OUTPUT
from vllm.v1.outputs import EMPTY_MODEL_RUNNER_OUTPUT
host = MixinHost()
host.get_omni_connector_output = lambda: OmniConnectorOutput(chunk_ready_req_ids={"req-1"})