[P/D] NIXL Integration (#17751)

Signed-off-by: ApostaC <yihua98@uchicago.edu>
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
Signed-off-by: rshaw@neuralmagic.com <robertgshaw2@gmail.com>
Signed-off-by: Robert Shaw <rshaw@neuralmagic.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Signed-off-by: Brent Salisbury <bsalisbu@redhat.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: ApostaC <yihua98@uchicago.edu>
Co-authored-by: Robert Shaw <rshaw@neuralmagic.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Tyler Michael Smith <tysmith@redhat.com>
Co-authored-by: Brent Salisbury <bsalisbu@redhat.com>
This commit is contained in:
Robert Shaw
2025-05-12 12:46:16 -04:00
committed by GitHub
parent 05a4324f8e
commit d19110204c
34 changed files with 2723 additions and 108 deletions

View File

@@ -8,6 +8,7 @@ import inspect
import json
import re
import textwrap
import uuid
import warnings
from collections import Counter
from contextlib import contextmanager
@@ -3438,6 +3439,9 @@ class KVTransferConfig:
"""The KV connector for vLLM to transmit KV caches between vLLM instances.
"""
engine_id: str = str(uuid.uuid4())
"""The engine id for KV transfers."""
kv_buffer_device: Optional[str] = "cuda"
"""The device used by kv connector to buffer the KV cache.
Currently only support 'cuda'."""
@@ -3448,7 +3452,7 @@ class KVTransferConfig:
kv_role: Optional[KVRole] = None
"""Whether this vLLM instance produces, consumes KV cache, or both. Choices
are 'kv_producer', 'kv_consumer', and 'both'."""
are 'kv_producer', 'kv_consumer', and 'kv_both'."""
kv_rank: Optional[int] = None
"""The rank of this vLLM instance in the KV cache transfer. Typical value: