PR #17794 Make graph_max_nodes vary by ubatch size

Make graph_max_nodes vary by ubatch size for models where chunking might explode the graph

pwilkin committed 247 days ago

Update src/llama-context.h

pwilkin committed 246 days ago

Add missing const

pwilkin committed 246 days ago

llama.cpp Make graph_max_nodes vary by ubatch size #17794 Merged