[P/D][V1] KV Connector API V1 (#15960)

Signed-off-by: ApostaC <yihua98@uchicago.edu>
Signed-off-by: rshaw@neuralmagic.com <robertgshaw2@gmail.com>
Signed-off-by: remi <remi@mistral.ai>
Co-authored-by: rshaw@neuralmagic.com <robertgshaw2@gmail.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Rémi Delacourt <54138269+Flechman@users.noreply.github.com>
Co-authored-by: Tyler Michael Smith <tysmith@redhat.com>
This commit is contained in:
Yihua Cheng
2025-04-17 13:22:40 -07:00
committed by GitHub
co-authored by rshaw@neuralmagic.com <robertgshaw2@gmail.com> Robert Shaw Rémi Delacourt Tyler Michael Smith
parent 0377b8310b
commit 3408e47159
24 changed files with 1377 additions and 83 deletions
+2 -1
View File
@@ -23,7 +23,8 @@ from vllm.attention.backends.abstract import AttentionState
from vllm.attention.backends.utils import CommonAttentionState
from vllm.config import CompilationLevel, VllmConfig
from vllm.core.scheduler import SchedulerOutputs
from vllm.distributed import get_kv_transfer_group, get_pp_group
from vllm.distributed import get_pp_group
from vllm.distributed.kv_transfer import get_kv_transfer_group
from vllm.distributed.parallel_state import (get_tensor_model_parallel_rank,
graph_capture)
from vllm.forward_context import get_forward_context, set_forward_context