[KV offload][1b/N] rename offloading to kv_offload (#25191)

Signed-off-by: Or Ozeri <oro@il.ibm.com>

.buildkite/test-pipeline.yaml

@@ -280,7 +280,7 @@ steps:
     # split the test to avoid interference
     - pytest -v -s v1/core
     - pytest -v -s v1/executor
-    - pytest -v -s v1/offloading
+    - pytest -v -s v1/kv_offload
     - pytest -v -s v1/sample
     - pytest -v -s v1/logits_processors
     - pytest -v -s v1/worker

tests/v1/offloading/test_worker.py → tests/v1/kv_offload/test_worker.py

 # SPDX-License-Identifier: Apache-2.0
 # SPDX-FileCopyrightText: Copyright contributors to the vLLM project
-from vllm.v1.offloading.abstract import LoadStoreSpec
-from vllm.v1.offloading.worker.worker import (OffloadingHandler,
+from vllm.v1.kv_offload.abstract import LoadStoreSpec
+from vllm.v1.kv_offload.worker.worker import (OffloadingHandler,
                                               OffloadingWorker, TransferResult,
                                               TransferSpec)
 

vllm/v1/offloading/mediums.py → vllm/v1/kv_offload/mediums.py

@@ -4,7 +4,7 @@ from abc import ABC
 
 import numpy as np
 
-from vllm.v1.offloading.abstract import LoadStoreSpec
+from vllm.v1.kv_offload.abstract import LoadStoreSpec
 
 
 class BlockIDsLoadStoreSpec(LoadStoreSpec, ABC):

vllm/v1/offloading/worker/worker.py → vllm/v1/kv_offload/worker/worker.py

@@ -3,7 +3,7 @@
 from abc import ABC, abstractmethod
 
 from vllm.logger import init_logger
-from vllm.v1.offloading.abstract import LoadStoreSpec
+from vllm.v1.kv_offload.abstract import LoadStoreSpec
 
 # a single transfer spec (src_blocks_spec, dst_blocks_spec)
 TransferSpec = tuple[LoadStoreSpec, LoadStoreSpec]