Implementing support for laguna arch

2026-07-29 11:46:09 -05:00
parent 0bcb7ca59a
commit 68f5d104a8
8 changed files with 234 additions and 189 deletions
@@ -20,6 +20,7 @@ struct llama_longhaul_cache {
    bool remap(int layer, ggml_tensor * ids);
    void release(int layer);

+    uint32_t capacity() const;
    uint32_t max_ubatch(uint32_t n_expert_used) const;
    const std::string & error() const;
    bool failed() const;