[Misc] Rename embedding classes to pooling (#10801)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2024-12-01 14:36:51 +08:00
committed by GitHub
parent f877a7d12a
commit d2f058e76c
25 changed files with 166 additions and 123 deletions

View File

@@ -8,10 +8,10 @@ from vllm.attention.backends.abstract import AttentionBackend
from vllm.attention.backends.utils import CommonAttentionState
from vllm.model_executor import SamplingMetadata
from vllm.model_executor.pooling_metadata import PoolingMetadata
from vllm.worker.embedding_model_runner import (
ModelInputForGPUWithPoolingMetadata)
from vllm.worker.model_runner import ModelInputForGPUWithSamplingMetadata
from vllm.worker.multi_step_model_runner import StatefulModelInput
from vllm.worker.pooling_model_runner import (
ModelInputForGPUWithPoolingMetadata)
class MockAttentionBackend(AttentionBackend):