biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Misc] Move CpuGpuBuffer to vllm/v1/utils.py (#23728)

Browse Source 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
This commit is contained in:
Woosuk Kwon
2025-08-27 03:25:00 -07:00
committed by GitHub
parent 6578e87365
commit 04ff1e43fb
4 changed files with 33 additions and 33 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
vllm/v1/worker/gpu_model_runner.py
View File

@@ -78,14 +78,14 @@ 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 CpuGpuBuffer
from vllm.v1.worker.gpu_input_batch import CachedRequestState, InputBatch
from vllm.v1.worker.kv_connector_model_runner_mixin import (
KVConnectorModelRunnerMixin, KVConnectorOutput)
from vllm.v1.worker.lora_model_runner_mixin import LoRAModelRunnerMixin
from .utils import (AttentionGroup, CpuGpuBuffer, MultiModalBudget,
bind_kv_cache, gather_mm_placeholders,
initialize_kv_cache_for_kv_sharing,
from .utils import (AttentionGroup, MultiModalBudget, bind_kv_cache,
gather_mm_placeholders, initialize_kv_cache_for_kv_sharing,
sanity_check_mm_encoder_outputs, scatter_mm_placeholders)
if TYPE_CHECKING: