[Feature] Support pd ep deployment with yiyan adapter (#4029)

* [Feature] Support mixed deployment with yiyan adapter in release2.2

* fix metrics

* add unit test

* add unit test

* add unit test

* Support pd ep deployment with yiyan adapter

* Support pd ep deployment with yiyan adapter

* refactor cache messager

* support scheduler v1 in PD

* suppport pd v1 + chunk prefill

* suppport pd v1 + chunk prefill

* add eplb

* support eplb

* support eplb

* support eplb

* support v1

* fix

* fix

* fix bug

* remove eplb support

* support prefix cache in P

* fix bug

* fix bug

* support one stop in V1

* fix bug

* fix ci

* fix ci

* fix

* fix

* fix

* fix

* fix

---------

Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>
This commit is contained in:
chenjian
2025-09-22 16:41:38 +08:00
committed by GitHub
parent 9845f0d010
commit 918ccdb123
22 changed files with 1838 additions and 343 deletions

View File

@@ -73,6 +73,7 @@ class Request:
guided_json_object: Optional[bool] = None,
enable_thinking: Optional[bool] = True,
trace_carrier: dict = dict(),
dp_rank: Optional[int] = None,
chat_template: Optional[str] = None,
image_start: int = 0,
video_start: int = 0,
@@ -145,6 +146,8 @@ class Request:
# extend block tables
self.use_extend_tables = False
self.extend_block_tables = []
# dp
self.dp_rank = dp_rank
@classmethod
def from_dict(cls, d: dict):
@@ -187,6 +190,7 @@ class Request:
image_end=d.get("image_end", 0),
video_end=d.get("video_end", 0),
audio_end=d.get("audio_end", 0),
dp_rank=d.get("dp_rank", None),
)
@property