forked from vllm-project/vllm
-
Notifications
You must be signed in to change notification settings - Fork 0
Open
Labels
enhancementNew feature or requestNew feature or requestvLLM-monitorReported by vLLM-monitorReported by vLLM-monitor
Description
vLLM PR 监控通知
PR 标题: [Feature] Enable TP + EP shared_experts overlap with router, 3.7% E2E performance improvement
PR 编号: vllm-project#28164
PR 链接: vllm-project#28164
变更的核心文件:
- vllm/model_executor/layers/fused_moe/layer.py
由GitHub Actions自动创建
Metadata
Metadata
Assignees
Labels
enhancementNew feature or requestNew feature or requestvLLM-monitorReported by vLLM-monitorReported by vLLM-monitor