[MISC] Move bind_kv_cache to worker module (#20900)

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
This commit is contained in:
wangxiyuan
2025-07-14 09:40:00 +00:00
committed by GitHub
parent 697ef765ee
commit 1e9438e0b0
6 changed files with 57 additions and 55 deletions
+2 -2
View File
@@ -62,13 +62,13 @@ from vllm.v1.spec_decode.eagle import EagleProposer
from vllm.v1.spec_decode.medusa import MedusaProposer
from vllm.v1.spec_decode.metadata import SpecDecodeMetadata
from vllm.v1.spec_decode.ngram_proposer import NgramProposer
from vllm.v1.utils import bind_kv_cache
from vllm.v1.worker.block_table import BlockTable
from vllm.v1.worker.gpu_input_batch import CachedRequestState, InputBatch
from vllm.v1.worker.lora_model_runner_mixin import LoRAModelRunnerMixin
from ..sample.logits_processor import LogitsProcessorManager
from .utils import (gather_mm_placeholders, initialize_kv_cache_for_kv_sharing,
from .utils import (bind_kv_cache, gather_mm_placeholders,
initialize_kv_cache_for_kv_sharing,
sanity_check_mm_encoder_outputs, scatter_mm_placeholders)
if TYPE_CHECKING: