Rename ngram_utils -> ngram_info (#11316)
This commit is contained in:
@@ -849,7 +849,7 @@ class CudaGraphRunner:
|
|||||||
)
|
)
|
||||||
|
|
||||||
elif self.model_runner.spec_algorithm.is_ngram():
|
elif self.model_runner.spec_algorithm.is_ngram():
|
||||||
from sglang.srt.speculative.ngram_utils import NgramVerifyInput
|
from sglang.srt.speculative.ngram_info import NgramVerifyInput
|
||||||
|
|
||||||
spec_info = NgramVerifyInput(
|
spec_info = NgramVerifyInput(
|
||||||
draft_token=None,
|
draft_token=None,
|
||||||
|
|||||||
@@ -11,7 +11,7 @@ from sglang.srt.managers.tp_worker import TpModelWorker
|
|||||||
from sglang.srt.model_executor.forward_batch_info import ForwardMode
|
from sglang.srt.model_executor.forward_batch_info import ForwardMode
|
||||||
from sglang.srt.server_args import ServerArgs
|
from sglang.srt.server_args import ServerArgs
|
||||||
from sglang.srt.speculative.cpp_ngram.ngram_cache import NgramCache
|
from sglang.srt.speculative.cpp_ngram.ngram_cache import NgramCache
|
||||||
from sglang.srt.speculative.ngram_utils import NgramVerifyInput
|
from sglang.srt.speculative.ngram_info import NgramVerifyInput
|
||||||
from sglang.srt.speculative.spec_info import SpeculativeAlgorithm
|
from sglang.srt.speculative.spec_info import SpeculativeAlgorithm
|
||||||
|
|
||||||
logger = logging.getLogger(__name__)
|
logger = logging.getLogger(__name__)
|
||||||
|
|||||||
@@ -1,7 +1,6 @@
|
|||||||
from __future__ import annotations
|
from __future__ import annotations
|
||||||
|
|
||||||
import logging
|
import logging
|
||||||
import os
|
|
||||||
import time
|
import time
|
||||||
from typing import TYPE_CHECKING, List
|
from typing import TYPE_CHECKING, List
|
||||||
|
|
||||||
|
|||||||
Reference in New Issue
Block a user