Run pre-commit to format files

Signed-off-by: Wei-Yu Lin <weiyulin@google.com>

vllm/model_executor/model_loader/default_loader.py

@@ -242,7 +242,7 @@ class DefaultModelLoader(BaseModelLoader):
                 )
 
         if current_platform.is_tpu():
-            from vllm.platforms.tpu import USE_TPU_INFERENCE
+            pass
 
         if self.counter_before_loading_weights == 0.0:
             self.counter_before_loading_weights = time.perf_counter()

vllm/platforms/tpu.py

@@ -1,34 +1,8 @@
 # SPDX-License-Identifier: Apache-2.0
 # SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
-import contextlib
-from typing import TYPE_CHECKING, Optional, cast
-
-import torch
-from tpu_info import device
-
-from vllm.attention.backends.registry import AttentionBackendEnum
-from vllm.inputs import ProcessorInputs, PromptType
 from vllm.logger import init_logger
 
-from .interface import Platform, PlatformEnum
-
-if TYPE_CHECKING:
-    from typing import TypeAlias
-
-    from vllm.attention.selector import AttentionSelectorConfig
-    from vllm.config import VllmConfig
-    from vllm.config.cache import BlockSize
-    from vllm.pooling_params import PoolingParams
-    from vllm.sampling_params import SamplingParams
-
-    ParamsType: TypeAlias = SamplingParams | PoolingParams
-else:
-    BlockSize = None
-    VllmConfig = None
-    PoolingParams = None
-    ParamsType = None
-
 logger = init_logger(__name__)
 
 
@@ -40,5 +14,7 @@ try:
     TpuPlatform = TpuInferencePlatform  # type: ignore
     USE_TPU_INFERENCE = True
 except ImportError:
-    logger.error("tpu_inference not found, please install tpu_inference to run vllm on TPU")
+    logger.error(
+        "tpu_inference not found, please install tpu_inference to run vllm on TPU"
+    )
     pass

vllm/v1/worker/tpu_worker.py

@@ -2,35 +2,10 @@
 # SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """A TPU worker class."""
 
-import os
+from typing import TypeVar
-from collections.abc import Callable
-from typing import Any, TypeVar
 
-import torch
-import torch.nn as nn
-
-import vllm.envs as envs
-from vllm.config import VllmConfig, set_current_vllm_config
-from vllm.distributed import (
-    ensure_model_parallel_initialized,
-    init_distributed_environment,
-)
-from vllm.distributed.kv_transfer import (
-    ensure_kv_transfer_initialized,
-)
 from vllm.logger import init_logger
-from vllm.lora.request import LoRARequest
-from vllm.model_executor import set_random_seed
-from vllm.platforms import current_platform
 from vllm.platforms.tpu import USE_TPU_INFERENCE
-from vllm.tasks import SupportedTask
-from vllm.utils.math_utils import cdiv
-from vllm.utils.torch_utils import STR_DTYPE_TO_TORCH_DTYPE
-from vllm.v1.core.sched.output import GrammarOutput, SchedulerOutput
-from vllm.v1.kv_cache_interface import AttentionSpec, KVCacheConfig, KVCacheSpec
-from vllm.v1.outputs import ModelRunnerOutput
-from vllm.v1.utils import report_usage_stats
-from vllm.v1.worker.utils import bind_kv_cache
 
 logger = init_logger(__name__)