apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-05 16:48:03 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

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

Browse Source 
* [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
Download Patch File Download Diff File Expand all files Collapse all files

14
fastdeploy/envs.py
View File

@@ -109,6 +109,12 @@ environment_variables: dict[str, Callable[[], Any]] = {
"FD_ZMQ_SEND_RESPONSE_SERVER_PORT": lambda: os.getenv("FD_ZMQ_SEND_RESPONSE_SERVER_PORT", "8201"),
# LLMEngine recieve control command port, used when FD_ENABLE_INTERNAL_ADAPTER=1
"FD_ZMQ_CONTROL_CMD_SERVER_PORTS": lambda: os.getenv("FD_ZMQ_CONTROL_CMD_SERVER_PORTS", "8202"),
# Whether to enable cache task in decode node
"FD_ENABLE_CACHE_TASK": lambda: os.getenv("FD_ENABLE_CACHE_TASK", "1"),
# Batched token timeout in EP
"FD_EP_BATCHED_TOKEN_TIMEOUT": lambda: float(os.getenv("FD_EP_BATCHED_TOKEN_TIMEOUT", "0.1")),
# Max pre-fetch requests number in PD
"FD_EP_MAX_PREFETCH_TASK_NUM": lambda: int(os.getenv("FD_EP_MAX_PREFETCH_TASK_NUM", "8")),
"FD_ENABLE_MODEL_LOAD_CACHE": lambda: bool(int(os.getenv("FD_ENABLE_MODEL_LOAD_CACHE", "0"))),
}
@@ -120,6 +126,14 @@ def __getattr__(name: str):
raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
def get_unique_name(self, name):
"""
Get unique name for config
"""
shm_uuid = os.getenv("SHM_UUID", "")
return name + f"_{shm_uuid}"
def __setattr__(name: str, value: Any):
assert name in environment_variables
environment_variables[name] = lambda: value