apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-05 08:37:06 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[Feature] Support mixed deployment with yiyan adapter in release22 (#3974)
Some checks failed
CE Compile Job / ce_job_pre_check (push) Has been cancelled
Details
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
Details
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
Details
CE Compile Job / Show Code Archive Output (push) Has been cancelled
Details
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
Details
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
Details
CE Compile Job / CE_UPLOAD (push) Has been cancelled
Details

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

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

* fix metrics

* add unit test

* add unit test

* add unit test

* add unit test

* add unit test

* add unit test
This commit is contained in:
chenjian
2025-09-10 16:01:13 +08:00
committed by GitHub
parent c4098d56a0
commit 4f8ff478b3
11 changed files with 892 additions and 167 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
fastdeploy/envs.py
View File

@@ -95,6 +95,14 @@ environment_variables: dict[str, Callable[[], Any]] = {
"FD_FOR_TORCH_MODEL_FORMAT": lambda: bool(int(os.getenv("FD_FOR_TORCH_MODEL_FORMAT", "0"))),
# force disable default chunked prefill
"FD_DISABLE_CHUNKED_PREFILL": lambda: bool(int(os.getenv("FD_DISABLE_CHUNKED_PREFILL", "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"),
}