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

Update model_loader deps and qqq quantization deps (#2220) (#2318)

Browse Source 
Co-authored-by: HandH1998 <1335248067@qq.com>
This commit is contained in:
Yineng Zhang
2024-12-02 23:22:13 +08:00
committed by GitHub
parent 33deca81b5
commit 85e1a6f3aa
58 changed files with 2363 additions and 366 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
python/sglang/srt/lora/lora.py
View File

@@ -31,7 +31,6 @@ from vllm.model_executor.layers.vocab_parallel_embedding import (
ParallelLMHead,
VocabParallelEmbedding,
)
from vllm.model_executor.model_loader.loader import DefaultModelLoader
from sglang.srt.layers.linear import (
ColumnParallelLinear,
@@ -40,6 +39,7 @@ from sglang.srt.layers.linear import (
RowParallelLinear,
)
from sglang.srt.model_executor.forward_batch_info import ForwardBatch, ForwardMode
from sglang.srt.model_loader.loader import DefaultModelLoader
class BaseLayerWithLoRA(nn.Module):