mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-10-05 00:33:03 +08:00
Fix chunked prefill (#3778)
Some checks failed
CE Compile Job / ce_job_pre_check (push) Has been cancelled
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
CE Compile Job / Show Code Archive Output (push) Has been cancelled
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
CE Compile Job / CE_UPLOAD (push) Has been cancelled
Some checks failed
CE Compile Job / ce_job_pre_check (push) Has been cancelled
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
CE Compile Job / Show Code Archive Output (push) Has been cancelled
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
CE Compile Job / CE_UPLOAD (push) Has been cancelled
* update enable chunked_prefill * update code * update code * update code
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