【开源发布】llama.cpp v5.3

llama.cpp（ggml-org/llama.cpp）发布 v5.3。更新说明：meta: support GLM-5.3 next sm tensor glm5-next : cont q_absorbed for -sm tensor with non-unified KV meta : keep GGML_OP_ARANGE in ggml.h order glm5-next : split MLA heads in pairs for -sm tensor The MLA cache has a single KV head, so the heads on a device are its GQA ratio. The HIP tile FA kernel for D=512 needs an even GQA ratio; with 3 devices the 16 heads of the test model were split 5/5/6 and it aborted. 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 o