lora : update API names (#11167)

ggml-ci

Author: ggerganov

common/common.cpp

@@ -910,12 +910,13 @@ struct common_init_result common_init_from_params(common_params & params) {
             return iparams;
         }
 
-        int err = llama_control_vector_apply(lctx,
-                                             cvec.data.data(),
-                                             cvec.data.size(),
-                                             cvec.n_embd,
-                                             params.control_vector_layer_start,
-                                             params.control_vector_layer_end);
+        int err = llama_apply_adapter_cvec(
+                lctx,
+                cvec.data.data(),
+                cvec.data.size(),
+                cvec.n_embd,
+                params.control_vector_layer_start,
+                params.control_vector_layer_end);
         if (err) {
             llama_free(lctx);
             llama_model_free(model);
@@ -926,8 +927,8 @@ struct common_init_result common_init_from_params(common_params & params) {
 
     // load and optionally apply lora adapters
     for (auto & la : params.lora_adapters) {
-        llama_lora_adapter_ptr lora;
-        lora.reset(llama_lora_adapter_init(model, la.path.c_str()));
+        llama_adapter_lora_ptr lora;
+        lora.reset(llama_adapter_lora_init(model, la.path.c_str()));
         if (lora == nullptr) {
             LOG_ERR("%s: failed to apply lora adapter '%s'\n", __func__, la.path.c_str());
             llama_free(lctx);
@@ -940,7 +941,7 @@ struct common_init_result common_init_from_params(common_params & params) {
     }
 
     if (!params.lora_init_without_apply) {
-        common_lora_adapters_apply(lctx, params.lora_adapters);
+        common_set_adapter_lora(lctx, params.lora_adapters);
     }
 
     if (params.sampling.ignore_eos && llama_token_eos(vocab) == LLAMA_TOKEN_NULL) {
@@ -1008,11 +1009,11 @@ struct common_init_result common_init_from_params(common_params & params) {
     return iparams;
 }
 
-void common_lora_adapters_apply(struct llama_context * ctx, std::vector<common_lora_adapter_info> & lora) {
-    llama_lora_adapter_clear(ctx);
+void common_set_adapter_lora(struct llama_context * ctx, std::vector<common_adapter_lora_info> & lora) {
+    llama_clear_adapter_lora(ctx);
     for (auto & la : lora) {
         if (la.scale != 0.0f) {
-            llama_lora_adapter_set(ctx, la.ptr, la.scale);
+            llama_set_adapter_lora(ctx, la.ptr, la.scale);
         }
     }
 }

common/common.h

@@ -24,11 +24,11 @@
 
 #define DEFAULT_MODEL_PATH "models/7B/ggml-model-f16.gguf"
 
-struct common_lora_adapter_info {
+struct common_adapter_lora_info {
     std::string path;
     float scale;
 
-    struct llama_lora_adapter * ptr;
+    struct llama_adapter_lora * ptr;
 };
 
 using llama_tokens = std::vector<llama_token>;
@@ -246,8 +246,8 @@ struct common_params {
     std::vector<std::string> antiprompt; // strings upon which more user input is prompted (a.k.a. reverse prompts)
     std::vector<llama_model_kv_override> kv_overrides;
 
-    bool lora_init_without_apply = false; // only load lora to memory, but do not apply it to ctx (user can manually apply lora later using llama_lora_adapter_apply)
-    std::vector<common_lora_adapter_info> lora_adapters; // lora adapter path with user defined scale
+    bool lora_init_without_apply = false; // only load lora to memory, but do not apply it to ctx (user can manually apply lora later using llama_adapter_lora_apply)
+    std::vector<common_adapter_lora_info> lora_adapters; // lora adapter path with user defined scale
 
     std::vector<common_control_vector_load_info> control_vectors; // control vector with user defined scale
 
@@ -481,7 +481,7 @@ struct common_init_result {
     llama_model_ptr   model;
     llama_context_ptr context;
 
-    std::vector<llama_lora_adapter_ptr> lora;
+    std::vector<llama_adapter_lora_ptr> lora;
 };
 
 struct common_init_result     common_init_from_params(common_params & params);
@@ -503,7 +503,7 @@ struct llama_model * common_load_model_from_hf(
     const struct llama_model_params & params);
 
 // clear LoRA adapters from context, then apply new list of adapters
-void common_lora_adapters_apply(struct llama_context * ctx, std::vector<common_lora_adapter_info> & lora);
+void common_set_adapter_lora(struct llama_context * ctx, std::vector<common_adapter_lora_info> & lora);
 
 //
 // Batch utils

examples/export-lora/export-lora.cpp

@@ -130,7 +130,7 @@ struct lora_merge_ctx {
 
     lora_merge_ctx(
             std::string & base_fname,
-            std::vector<common_lora_adapter_info> & lora_files,
+            std::vector<common_adapter_lora_info> & lora_files,
             std::string & outfile,
             int n_threads) : base_model(base_fname, 0), n_threads(n_threads), fout(outfile, std::ios::binary) {
         fout.exceptions(std::ofstream::failbit); // fail fast on write errors

examples/server/server.cpp

@@ -98,7 +98,7 @@ struct slot_params {
     int64_t t_max_prompt_ms  = -1; // TODO: implement
     int64_t t_max_predict_ms = -1; // if positive, limit the generation phase to this time limit
 
-    std::vector<common_lora_adapter_info> lora;
+    std::vector<common_adapter_lora_info> lora;
 
     std::vector<std::string> antiprompt;
     std::vector<std::string> response_fields;
@@ -198,7 +198,7 @@ struct server_task {
     bool metrics_reset_bucket = false;
 
     // used by SERVER_TASK_TYPE_SET_LORA
-    std::vector<common_lora_adapter_info> set_lora;
+    std::vector<common_adapter_lora_info> set_lora;
 
     server_task(server_task_type type) : type(type) {}
 
@@ -1133,7 +1133,7 @@ struct server_slot {
 
     common_speculative * spec = nullptr;
 
-    std::vector<common_lora_adapter_info> lora;
+    std::vector<common_adapter_lora_info> lora;
 
     // the index relative to completion multi-task request
     size_t index = 0;
@@ -2934,7 +2934,7 @@ struct server_context {
             // make sure we're in the right embedding mode
             llama_set_embeddings(ctx, slot_batched->is_non_causal());
             // apply lora, only need to do it once per batch
-            common_lora_adapters_apply(ctx, slot_batched->lora);
+            common_set_adapter_lora(ctx, slot_batched->lora);
         }
 
         // process the created batch of tokens

examples/server/utils.hpp

@@ -804,8 +804,8 @@ static std::vector<llama_token_data> get_token_probabilities(llama_context * ctx
 }
 
 static bool are_lora_equal(
-        const std::vector<common_lora_adapter_info> & l1,
-        const std::vector<common_lora_adapter_info> & l2) {
+        const std::vector<common_adapter_lora_info> & l1,
+        const std::vector<common_adapter_lora_info> & l2) {
     if (l1.size() != l2.size()) {
         return false;
     }
@@ -819,10 +819,10 @@ static bool are_lora_equal(
 }
 
 // parse lora config from JSON request, returned a copy of lora_base with updated scale
-static std::vector<common_lora_adapter_info> parse_lora_request(
-        const std::vector<common_lora_adapter_info> & lora_base,
+static std::vector<common_adapter_lora_info> parse_lora_request(
+        const std::vector<common_adapter_lora_info> & lora_base,
         const json & data) {
-    std::vector<common_lora_adapter_info> lora(lora_base);
+    std::vector<common_adapter_lora_info> lora(lora_base);
     int max_idx = lora.size();
 
     // clear existing value

include/llama-cpp.h

@@ -20,11 +20,11 @@ struct llama_sampler_deleter {
     void operator()(llama_sampler * sampler) { llama_sampler_free(sampler); }
 };
 
-struct llama_lora_adapter_deleter {
-    void operator()(llama_lora_adapter * lora_adapter) { llama_lora_adapter_free(lora_adapter); }
+struct llama_adapter_lora_deleter {
+    void operator()(llama_adapter_lora * adapter) { llama_adapter_lora_free(adapter); }
 };
 
 typedef std::unique_ptr<llama_model, llama_model_deleter> llama_model_ptr;
 typedef std::unique_ptr<llama_context, llama_context_deleter> llama_context_ptr;
 typedef std::unique_ptr<llama_sampler, llama_sampler_deleter> llama_sampler_ptr;
-typedef std::unique_ptr<llama_lora_adapter, llama_lora_adapter_deleter> llama_lora_adapter_ptr;
+typedef std::unique_ptr<llama_adapter_lora, llama_adapter_lora_deleter> llama_adapter_lora_ptr;

include/llama.h

@@ -385,8 +385,7 @@ extern "C" {
     } llama_chat_message;
 
     // lora adapter
-    // TODO: rename to llama_adapter_lora
-    struct llama_lora_adapter;
+    struct llama_adapter_lora;
 
     // Helpers for getting default parameters
     // TODO: update API to start accepting pointers to params structs (https://github.com/ggerganov/llama.cpp/discussions/9172)
@@ -520,44 +519,40 @@ extern "C" {
     //
 
     // Load a LoRA adapter from file
-    // TODO: rename to llama_adapter_lora_init
-    LLAMA_API struct llama_lora_adapter * llama_lora_adapter_init(
+    LLAMA_API struct llama_adapter_lora * llama_adapter_lora_init(
             struct llama_model * model,
             const char * path_lora);
 
+    // Manually free a LoRA adapter
+    // Note: loaded adapters will be free when the associated model is deleted
+    LLAMA_API void llama_adapter_lora_free(struct llama_adapter_lora * adapter);
+
+    // The following functions operate on a llama_context, hence the naming: llama_verb_...
+
     // Add a loaded LoRA adapter to given context
     // This will not modify model's weight
-    // TODO: rename to llama_set_adapter_lora
-    LLAMA_API int32_t llama_lora_adapter_set(
+    LLAMA_API int32_t llama_set_adapter_lora(
             struct llama_context * ctx,
-            struct llama_lora_adapter * adapter,
+            struct llama_adapter_lora * adapter,
             float scale);
 
     // Remove a specific LoRA adapter from given context
     // Return -1 if the adapter is not present in the context
-    // TODO: rename to llama_rm_adapter_lora
-    LLAMA_API int32_t llama_lora_adapter_remove(
+    LLAMA_API int32_t llama_rm_adapter_lora(
             struct llama_context * ctx,
-            struct llama_lora_adapter * adapter);
+            struct llama_adapter_lora * adapter);
 
     // Remove all LoRA adapters from given context
-    // TODO: rename to llama_clear_adapter_lora
-    LLAMA_API void llama_lora_adapter_clear(struct llama_context * ctx);
-
-    // Manually free a LoRA adapter
-    // Note: loaded adapters will be free when the associated model is deleted
-    // TODO: rename to llama_adapter_lora_free
-    LLAMA_API void llama_lora_adapter_free(struct llama_lora_adapter * adapter);
+    LLAMA_API void llama_clear_adapter_lora(struct llama_context * ctx);
 
     // Apply a loaded control vector to a llama_context, or if data is NULL, clear
     // the currently loaded vector.
     // n_embd should be the size of a single layer's control, and data should point
     // to an n_embd x n_layers buffer starting from layer 1.
     // il_start and il_end are the layer range the vector should apply to (both inclusive)
     // See llama_control_vector_load in common to load a control vector.
-    // TODO: rename to llama_adapter_cvec_apply
-    LLAMA_API int32_t llama_control_vector_apply(
-            struct llama_context * lctx,
+    LLAMA_API int32_t llama_apply_adapter_cvec(
+            struct llama_context * ctx,
                      const float * data,
                           size_t   len,
                          int32_t   n_embd,