[doc] updated inference readme (#5343)

This commit is contained in:
Frank Lee
2024-02-02 14:31:10 +08:00
committed by GitHub
parent e76acbb076
commit 027aa1043f
10 changed files with 82 additions and 33 deletions

View File

@@ -0,0 +1,4 @@
from .engine import InferenceEngine
from .request_handler import RequestHandler
__all__ = ["InferenceEngine", "RequestHandler"]

View File

@@ -17,6 +17,8 @@ from colossalai.shardformer.policies.base_policy import Policy
from .request_handler import RequestHandler
__all__ = ["InferenceEngine"]
PP_AXIS, TP_AXIS = 0, 1
_supported_models = [

View File

@@ -11,6 +11,8 @@ from colossalai.inference.sampler import *
from colossalai.inference.struct import BatchInfo, RequestStatus, Sequence
from colossalai.logging import get_dist_logger
__all__ = ["RunningList", "RequestHandler"]
logger = get_dist_logger(__name__)