mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-10-07 09:31:35 +08:00
[Feature] Support ep pd with external module (#3194)
* Support external module * Support external module * Support external module * Support external module * refactor code to make it more clear * refactor code to make it more clear * refactor code to make it more clear * refactor code to make it more clear * fix according to review * fix according to review * fix according to review * fix according to review * fix according to review * fix according to review * fix bug * fix bug * fix bug * merge --------- Co-authored-by: root <root@tjdm-inf-sci-k8s-hzz2-h12ni8-0202.tjdm.baidu.com>
This commit is contained in:
@@ -80,6 +80,14 @@ environment_variables: dict[str, Callable[[], Any]] = {
|
||||
"EXPORTER_OTLP_HEADERS": lambda: os.getenv("EXPORTER_OTLP_HEADERS"),
|
||||
# enable kv cache block scheduler v1 (no need for kv_cache_ratio)
|
||||
"ENABLE_V1_KVCACHE_SCHEDULER": lambda: int(os.getenv("ENABLE_V1_KVCACHE_SCHEDULER", "0")),
|
||||
# enable internal module to access LLMEngine.
|
||||
"FD_ENABLE_INTERNAL_ADAPTER": lambda: int(os.getenv("FD_ENABLE_INTERNAL_ADAPTER", "0")),
|
||||
# LLMEngine recieve requests port, used when FD_ENABLE_INTERNAL_ADAPTER=1
|
||||
"FD_ZMQ_RECV_REQUEST_SERVER_PORT": lambda: os.getenv("FD_ZMQ_RECV_REQUEST_SERVER_PORT", "8200"),
|
||||
# LLMEngine send response port, used when FD_ENABLE_INTERNAL_ADAPTER=1
|
||||
"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 use PLUGINS.
|
||||
"FD_PLUGINS": lambda: None if "FD_PLUGINS" not in os.environ else os.environ["FD_PLUGINS"].split(","),
|
||||
}
|
||||
|
Reference in New Issue
Block a user