Alexander Korolev
|
ef03b8c784
feat: auto-scale PP when pipeline_parallel_size == required_nodes
|
4 달 전 |
Alexander Korolev
|
b5615f604d
fix(recipe): switch GLM-5.2 from SGLang to vLLM
|
4 달 전 |
Alexander Korolev
|
3d35c82535
feat(recipe): add GLM-5.2 NVFP4 recipe (4-node SGLang)
|
4 달 전 |