[Distributed][Model] Rank-based Component Creation for Pipeline Parallelism Memory Optimization#6455
Merged
youkaichao merged 7 commits intovllm-project:mainfrom wushidonguc:pp-optimizationJul 17, 2024
+38-27
Commits
Commits on Jul 16, 2024
- committed
- committed
- committed
- committed
- committed
- committed
- committed
