EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

move more files under srt/utils (#11285)

Browse Source
This commit is contained in:
Lianmin Zheng
2025-10-09 16:46:15 -07:00
committed by GitHub
parent 758b887ad1
commit 9b8ebb2798
28 changed files with 96 additions and 55 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
python/sglang/srt/model_executor/model_runner.py
View File

@@ -117,15 +117,9 @@ from sglang.srt.model_loader.remote_instance_weight_loader_utils import (
)
from sglang.srt.model_loader.utils import set_default_torch_dtype
from sglang.srt.model_loader.weight_utils import default_weight_loader
from sglang.srt.offloader import (
create_offloader_from_server_args,
get_offloader,
set_offloader,
)
from sglang.srt.sampling.sampling_batch_info import SamplingBatchInfo
from sglang.srt.server_args import ServerArgs
from sglang.srt.speculative.spec_info import SpeculativeAlgorithm
from sglang.srt.torch_memory_saver_adapter import TorchMemorySaverAdapter
from sglang.srt.utils import (
MultiprocessingSerializer,
cpu_has_amx_support,
@@ -148,7 +142,13 @@ from sglang.srt.utils import (
set_cuda_arch,
slow_rank_detector,
)
from sglang.srt.utils.offloader import (
create_offloader_from_server_args,
get_offloader,
set_offloader,
)
from sglang.srt.utils.patch_torch import monkey_patch_torch_reductions
from sglang.srt.utils.torch_memory_saver_adapter import TorchMemorySaverAdapter
from sglang.srt.weight_sync.tensor_bucket import (
FlattenedTensorBucket,
FlattenedTensorMetadata,