llama.cpp

933b9f3d - meta : keep the split for views inside one slab of the split axis

meta : keep the split for views inside one slab of the split axis With a non-unified KV cache, build_attn_mha splits q into streams with a view. For a permuted q, e.g. the absorbed query of glm5-next, that view aborted with "view of permuted tensor not implemented". The split is now kept if every other dim of the source and the view stays inside one slab of the split axis. The per-device strides are only rescaled above it. From tetherto/qvac-fabric-llm.cpp#353. Co-authored-by: Pratik Narola <pratik.narola@tether.io>