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:
Ying Sheng
2024-05-27 21:24:10 -07:00
committed by GitHub
parent 565d727409
commit 0463f7fb52
32 changed files with 580 additions and 181 deletions

View File

@@ -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):