NUMA-aware tensor parallelism for CPU inference#3320

Open

MagellaX wants to merge 9 commits intomlc-ai:mainfrom

MagellaX:feat/numa-tensor-parallel

Commits on Jul 2, 2025

test(lora): add end-to-end LoRA integration tests
MagellaX
committed

Commits on Jul 4, 2025

test(lora): update CMakeLists and setup.py for LoRA integration
MagellaX
committed

Commits on Jul 5, 2025

fix(lora): update serving engine for LoRA integration
MagellaX
committed

Commits on Jul 6, 2025

Commits on Jul 7, 2025

fix(cli): clean up CMakeLists and lora_manager.cc for CLI interface
MagellaX
committed

Commits on Jul 11, 2025

fix(cli): update CMakeLists, serve engine and LoRA init for CLI interface
MagellaX
committed

Commits on Aug 30, 2025