[Misc] Improve LoRA spelling (#13831)

vllm/worker/neuron_worker.py

@@ -13,11 +13,11 @@ from vllm.model_executor.layers.sampler import SamplerOutput
 from vllm.sequence import ExecuteModelRequest
 from vllm.worker.neuron_model_runner import NeuronModelRunner
 from vllm.worker.worker_base import (LocalOrDistributedWorkerBase,
-                                     LoraNotSupportedWorkerBase, WorkerBase,
+                                     LoRANotSupportedWorkerBase, WorkerBase,
                                      WorkerInput)
 
 
-class NeuronWorker(LoraNotSupportedWorkerBase, LocalOrDistributedWorkerBase):
+class NeuronWorker(LoRANotSupportedWorkerBase, LocalOrDistributedWorkerBase):
     """A worker class that executes the model on a group of neuron cores.
     """
 

vllm/worker/openvino_worker.py

@@ -24,7 +24,7 @@ from vllm.sampling_params import SamplingParams
 from vllm.sequence import ExecuteModelRequest, SequenceGroupMetadata
 from vllm.utils import bind_kv_cache
 from vllm.worker.openvino_model_runner import OpenVINOModelRunner
-from vllm.worker.worker_base import LoraNotSupportedWorkerBase, WorkerBase
+from vllm.worker.worker_base import LoRANotSupportedWorkerBase, WorkerBase
 
 logger = init_logger(__name__)
 
@@ -203,7 +203,7 @@ class OpenVINOCacheEngine:
         return dtype_size * total
 
 
-class OpenVINOWorker(LoraNotSupportedWorkerBase):
+class OpenVINOWorker(LoRANotSupportedWorkerBase):
     """A worker class that executes the model on OpenVINO backend.
 
     Each worker is associated with a single OpenVINO device. The worker is

vllm/worker/tpu_worker.py

@@ -17,13 +17,13 @@ from vllm.sequence import ExecuteModelRequest
 from vllm.utils import STR_DTYPE_TO_TORCH_DTYPE, bind_kv_cache, get_dtype_size
 from vllm.worker.tpu_model_runner import ExecutionMode, TPUModelRunner
 from vllm.worker.worker_base import (LocalOrDistributedWorkerBase,
-                                     LoraNotSupportedWorkerBase, WorkerBase,
+                                     LoRANotSupportedWorkerBase, WorkerBase,
                                      WorkerInput)
 
 logger = init_logger(__name__)
 
 
-class TPUWorker(LoraNotSupportedWorkerBase, LocalOrDistributedWorkerBase):
+class TPUWorker(LoRANotSupportedWorkerBase, LocalOrDistributedWorkerBase):
 
     def __init__(
         self,

vllm/worker/worker_base.py

@@ -189,7 +189,7 @@ class DelegateWorkerBase(WorkerBase):
         return getattr(self.worker, attr)
 
 
-class LoraNotSupportedWorkerBase(WorkerBase):
+class LoRANotSupportedWorkerBase(WorkerBase):
     """Partial implementation of WorkerBase that raises exceptions when LoRA
     methods are invoked.
     """

vllm/worker/xpu_worker.py

@@ -18,13 +18,13 @@ from vllm.model_executor import set_random_seed
 from vllm.platforms import current_platform
 from vllm.worker.cache_engine import CacheEngine
 from vllm.worker.worker import Worker
-from vllm.worker.worker_base import LoraNotSupportedWorkerBase, WorkerBase
+from vllm.worker.worker_base import LoRANotSupportedWorkerBase, WorkerBase
 from vllm.worker.xpu_model_runner import XPUModelRunner
 
 logger = init_logger(__name__)
 
 
-class XPUWorker(LoraNotSupportedWorkerBase, Worker):
+class XPUWorker(LoRANotSupportedWorkerBase, Worker):
     """A worker class that executes (a partition of) the model on a GPU.
     
     Each worker is associated with a single XPU device. The worker is