mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-10-06 17:17:14 +08:00
[BugFix] Fix chunked prefill (#3759)
* add error traceback info * update error msg * update code * default enable chunked prefill * update code * update code * add envs * update code * update enable chunked_prefill * update code * update code * update code * update code * update code --------- Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
This commit is contained in:
@@ -93,8 +93,8 @@ environment_variables: dict[str, Callable[[], Any]] = {
|
||||
# enable multi api server
|
||||
"FD_ENABLE_MULTI_API_SERVER": lambda: bool(int(os.getenv("FD_ENABLE_MULTI_API_SERVER", "0"))),
|
||||
"FD_FOR_TORCH_MODEL_FORMAT": lambda: bool(int(os.getenv("FD_FOR_TORCH_MODEL_FORMAT", "0"))),
|
||||
# force enable chunked prefill
|
||||
"FD_FORCE_CHUNKED_PREFILL": lambda: bool(int(os.getenv("FD_FORCE_CHUNKED_PREFILL", "0"))),
|
||||
# force disable default chunked prefill
|
||||
"FD_DISABLE_CHUNKED_PREFILL": lambda: bool(int(os.getenv("FD_DISABLE_CHUNKED_PREFILL", "0"))),
|
||||
}
|
||||
|
||||
|
||||
|
Reference in New Issue
Block a user