Add tokenizer longhaul cache

2026-07-30 23:32:52 -05:00
parent a673afad85
commit e0665b1042
21 changed files with 1078 additions and 23 deletions
@@ -360,6 +360,8 @@ extern "C" {
        bool no_alloc;        // only load metadata and simulate memory allocations

        uint64_t longhaul_cache_bytes; // routed expert cache size for LLAMA_LOAD_MODE_LONGHAUL
+        bool tokenizer_longhaul;       // page Qwen3.5/Laguna tokenizer indexes through a bounded cache
+        uint64_t tokenizer_longhaul_cache_bytes; // tokenizer-longhaul RAM cache budget
    };

    struct llama_sampler_seq_config {