Skip to content

GitLab

Unverified Commit 33d5e29b authored by Chenyaaang's avatar Chenyaaang Committed by GitHub
Browse files

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


Signed-off-by: default avatarChenyaaang <chenyangli@google.com>
parent 4671ac6e
Hide whitespace changes
Inline Side-by-side
Showing with 2 additions and 0 deletions
tests/v1/tpu/worker/test_tpu_model_runner.py
View file @ 33d5e29b
...@@ -6,6 +6,7 @@ import pytest ...@@ -6,6 +6,7 @@ import pytest
from vllm.attention.layer import Attention from vllm.attention.layer import Attention
from vllm.config import (CacheConfig, ModelConfig, SchedulerConfig, VllmConfig, from vllm.config import (CacheConfig, ModelConfig, SchedulerConfig, VllmConfig,
set_current_vllm_config) set_current_vllm_config)
from vllm.pooling_params import PoolingParams
from vllm.sampling_params import SamplingParams from vllm.sampling_params import SamplingParams
from vllm.utils import GiB_bytes from vllm.utils import GiB_bytes
from vllm.v1.core.kv_cache_utils import (estimate_max_model_len, from vllm.v1.core.kv_cache_utils import (estimate_max_model_len,
...@@ -71,6 +72,7 @@ def _schedule_new_request(*req_ids: str) -> SchedulerOutput: ...@@ -71,6 +72,7 @@ def _schedule_new_request(*req_ids: str) -> SchedulerOutput:
mm_hashes=[], mm_hashes=[],
mm_positions=[], mm_positions=[],
sampling_params=SamplingParams(), sampling_params=SamplingParams(),
pooling_params=PoolingParams(),
block_ids=([0], ), # block_ids should be tuple[list[int]] block_ids=([0], ), # block_ids should be tuple[list[int]]
num_computed_tokens=0, num_computed_tokens=0,
lora_request=None, lora_request=None,
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment