input_batch.py -> gpu_input_batch.py

Signed-off-by: Varun Sundar Rabindranath <[email protected]>
vllm-project · Dec 6, 2024 · d21df49 · d21df49
1 parent 98b24d7
commit d21df49
Show file tree

Hide file tree

Showing 3 changed files with 2 additions and 2 deletions.
diff --git a/vllm/v1/worker/input_batch.py → vllm/v1/worker/gpu_input_batch.py b/vllm/v1/worker/input_batch.py → vllm/v1/worker/gpu_input_batch.py
diff --git a/vllm/v1/worker/gpu_model_runner.py b/vllm/v1/worker/gpu_model_runner.py
@@ -21,7 +21,7 @@
                                                    FlashAttentionMetadata)
 from vllm.v1.outputs import ModelRunnerOutput
 from vllm.v1.sample.metadata import SamplingMetadata
-from vllm.v1.worker.input_batch import CachedRequestState, InputBatch
+from vllm.v1.worker.gpu_input_batch import CachedRequestState, InputBatch
 from vllm.v1.worker.lora_model_runner_mixin import LoRAModelRunnerMixin
 
 if TYPE_CHECKING:

diff --git a/vllm/v1/worker/lora_model_runner_mixin.py b/vllm/v1/worker/lora_model_runner_mixin.py
@@ -14,7 +14,7 @@
 from vllm.lora.request import LoRARequest
 from vllm.lora.worker_manager import LRUCacheWorkerLoRAManager
 from vllm.model_executor.models import supports_lora, supports_multimodal
-from vllm.v1.worker.input_batch import InputBatch
+from vllm.v1.worker.gpu_input_batch import InputBatch
 
 logger = init_logger(__name__)