xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-10 03:15:20 +08:00
Code Issues Packages Projects Releases Wiki Activity

[TPU] Fix tpu model runner test (#19995)

Browse Source 
Signed-off-by: Chenyaaang <chenyangli@google.com>
This commit is contained in:
Chenyaaang 2025-06-23 16:04:28 -07:00 committed by GitHub
parent 4671ac6e2a
commit 33d5e29be9
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
tests/v1/tpu/worker/test_tpu_model_runner.py
View File

@ -6,6 +6,7 @@ import pytest
from vllm.attention.layer import Attention
from vllm.config import (CacheConfig, ModelConfig, SchedulerConfig, VllmConfig,
set_current_vllm_config)
from vllm.pooling_params import PoolingParams
from vllm.sampling_params import SamplingParams
from vllm.utils import GiB_bytes
from vllm.v1.core.kv_cache_utils import (estimate_max_model_len,
@ -71,6 +72,7 @@ def _schedule_new_request(*req_ids: str) -> SchedulerOutput:
mm_hashes=[],
mm_positions=[],
sampling_params=SamplingParams(),
pooling_params=PoolingParams(),
block_ids=([0], ), # block_ids should be tuple[list[int]]
num_computed_tokens=0,
lora_request=None,