Support data parallelism (static) (#480)
Co-authored-by: Ying Sheng <ying.sheng@databricks.com> Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com> Co-authored-by: Liangsheng Yin <hnyls2002@gmail.com> Co-authored-by: Zhiqiang Xie <xiezhq@stanford.edu>
This commit is contained in:
@@ -29,7 +29,7 @@ from vllm.transformers_utils.configs.dbrx import DbrxConfig
|
||||
|
||||
from sglang.srt.layers.logits_processor import LogitsProcessor
|
||||
from sglang.srt.layers.radix_attention import RadixAttention
|
||||
from sglang.srt.managers.router.model_runner import InputMetadata
|
||||
from sglang.srt.managers.controller.model_runner import InputMetadata
|
||||
|
||||
|
||||
class DbrxRouter(nn.Module):
|
||||
|
||||
Reference in New Issue
Block a user