llama.cpp b11339 修复 kpool 重池化边界越界
原标题：b11339
AI 摘要
llama.cpp 发布 b11339 版本，修复了 kpool 重新池化边界问题：当批次填满整个缓存时，n_tokens/kpool + n_seqs_unq 的边界会超出 n_pool_real，导致首次全上下文解码构建的图张量大于预留空间，在 GGML_SCHED_DEBUG_REALLOC=1 下触发图重分配中止。修复方式是将边界钳制到 n_pool_real/n_pool_max。该版本同时提供 macOS、Linux、Windows、Android 等多平台预编译二进制。
正文节选
<details open> llama : clamp kpool re-pool bound to existing pools (#29805) * tests : simplify function signature * llama : clamp kpool re-pool bound to existing pools The n_tokens/kpool + n_seqs_unq bound on n_new_g overshoots when a batch fills the whole cache: n_ctx tokens complete exactly n_ctx/kpool pools, so the +1 pads new_pool_idxs/new_pool_rep one entry past n_pool_real. Graph reserve only covers n_pool_real entries, so the first full-context decode builds bigger tensors than reserv