server : host-memory prompt caching (ggml-org#16391)

* minor : code style

* server : fix prompt similarity calculation

* server : initial host-memory prompt caching

* cont

* server : refactor

* cont

* cont : make the server task of the slot const

* cont : minor [no ci]

* server : cache prompts and checkpoints only for completion tasks

* server : improve prompt caching logic

* cont : fix check for number of cached prompts [no ci]

* server : improve caching logic, add -cram CLI arg

* server : print prompt mismatch info

* cont : better naming [no ci]

* server : improve prompt cache loading logic

* server : add option to debug the slot contents (ggml-org#16482)

* server : add option to debug the slot contents

* Update tools/server/server.cpp

---------

Co-authored-by: Xuan-Son Nguyen <son@huggingface.co>

* server : add option to disable prompt cache

---------

Co-authored-by: Xuan-Son Nguyen <son@huggingface.co>

Author: ggerganov

common/arg.cpp

@@ -1935,6 +1935,14 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
             params.n_ctx_checkpoints = value;
         }
     ).set_env("LLAMA_ARG_CTX_CHECKPOINTS").set_examples({LLAMA_EXAMPLE_SERVER}));
+    add_opt(common_arg(
+        {"--cache-ram", "-cram"}, "N",
+        string_format("set the maximum cache size in MiB (default: %d, -1 - no limit, 0 - disable)\n"
+            "[(more info)](https://github.com/ggml-org/llama.cpp/pull/16391)", params.cache_ram_mib),
+        [](common_params & params, int value) {
+            params.cache_ram_mib = value;
+        }
+    ).set_env("LLAMA_ARG_CACHE_RAM").set_examples({LLAMA_EXAMPLE_SERVER}));
     add_opt(common_arg(
         {"--kv-unified", "-kvu"},
         string_format("use single unified KV buffer for the KV cache of all sequences (default: %s)\n"

common/chat.h

@@ -33,8 +33,8 @@ struct common_chat_msg_content_part {
 struct common_chat_msg {
     std::string role;
     std::string content;
-    std::vector<common_chat_msg_content_part> content_parts = {};
-    std::vector<common_chat_tool_call> tool_calls = {};
+    std::vector<common_chat_msg_content_part> content_parts;
+    std::vector<common_chat_tool_call> tool_calls;
     std::string reasoning_content;
     std::string tool_name;
     std::string tool_call_id;
@@ -44,7 +44,7 @@ struct common_chat_msg {
     bool empty() const {
         return content.empty() && content_parts.empty() && tool_calls.empty() && reasoning_content.empty() && tool_name.empty() && tool_call_id.empty();
     }
-    void ensure_tool_call_ids_set(std::vector<std::string> & ids_cache, const std::function<std::string()> & gen_tool_call_id) {
+    void set_tool_call_ids(std::vector<std::string> & ids_cache, const std::function<std::string()> & gen_tool_call_id) {
         for (auto i = 0u; i < tool_calls.size(); i++) {
             if (ids_cache.size() <= i) {
                 auto id = tool_calls[i].id;

common/common.h

@@ -378,7 +378,7 @@ struct common_params {
     bool simple_io         = false; // improves compatibility with subprocesses and limited consoles
     bool cont_batching     = true;  // insert new sequences for decoding on-the-fly
     bool no_perf           = false; // disable performance metrics
-    bool ctx_shift         = false;  // context shift on infinite text generation
+    bool ctx_shift         = false; // context shift on infinite text generation
     bool swa_full          = false; // use full-size SWA cache (https://github.com/ggml-org/llama.cpp/pull/13194#issuecomment-2868343055)
     bool kv_unified        = false; // enable unified KV cache
 
@@ -425,7 +425,8 @@ struct common_params {
     int32_t timeout_write     = timeout_read; // http write timeout in seconds
     int32_t n_threads_http    = -1;           // number of threads to process HTTP requests (TODO: support threadpool)
     int32_t n_cache_reuse     = 0;            // min chunk size to reuse from the cache via KV shifting
-    int32_t n_ctx_checkpoints = 3;            // max number of context checkpoints per slot
+    int32_t n_ctx_checkpoints = 8;            // max number of context checkpoints per slot
+    int32_t cache_ram_mib     = 8192;         // 0 = no limit, 1 = 1 MiB, etc.
 
     std::string hostname      = "127.0.0.1";
     std::string public_path   = "";                                                                         // NOLINT

src/llama-kv-cache.cpp

@@ -123,11 +123,8 @@ llama_kv_cache::llama_kv_cache(
             throw std::runtime_error("failed to create ggml context for kv cache");
         }
 
-        ggml_tensor * k;
-        ggml_tensor * v;
-
-        k = ggml_new_tensor_3d(ctx, type_k, n_embd_k_gqa, kv_size, n_stream);
-        v = ggml_new_tensor_3d(ctx, type_v, n_embd_v_gqa, kv_size, n_stream);
+        ggml_tensor * k = ggml_new_tensor_3d(ctx, type_k, n_embd_k_gqa, kv_size, n_stream);
+        ggml_tensor * v = ggml_new_tensor_3d(ctx, type_v, n_embd_v_gqa, kv_size, n_stream);
 
         ggml_format_name(k, "cache_k_l%d", il);
         ggml_format_name(v, "cache_v_l%d", il);