cui-llama.rn 1.7.3 → 1.7.6

package/cpp/rn-llama.h

@@ -3,6 +3,7 @@
 
 #include <sstream>
 #include <iostream>
+#include <thread>
 #include "chat.h"
 #include "common.h"
 #include "ggml.h"
@@ -10,10 +11,13 @@
 #include "llama.h"
 #include "llama-impl.h"
 #include "sampling.h"
+#include "nlohmann/json.hpp"
 #if defined(__ANDROID__)
 #include <android/log.h>
 #endif
 
+using json = nlohmann::ordered_json;
+
 namespace rnllama {
 
 std::string tokens_to_output_formatted_string(const llama_context *ctx, const llama_token token);
@@ -43,6 +47,8 @@ struct completion_token_output
 
 struct llama_rn_context_mtmd;
 
+struct llama_rn_context_vocoder;
+
 struct llama_rn_tokenize_result {
     std::vector<llama_token> tokens;
     bool has_media = false;
@@ -51,6 +57,12 @@ struct llama_rn_tokenize_result {
     std::vector<size_t> chunk_pos_media; // media only
 };
 
+enum tts_type {
+    UNKNOWN = -1,
+    OUTETTS_V0_2 = 1,
+    OUTETTS_V0_3 = 2,
+};
+
 // Main context class
 struct llama_rn_context {
     bool is_predicting = false;
@@ -58,6 +70,7 @@ struct llama_rn_context {
     bool has_next_token = false;
     std::string generated_text;
     std::vector<completion_token_output> generated_token_probs;
+    std::vector<llama_token> audio_tokens;
 
     size_t num_prompt_tokens = 0;
     size_t num_tokens_predicted = 0;
@@ -69,6 +82,9 @@ struct llama_rn_context {
     common_params params;
     common_init_result llama_init;
 
+    bool next_token_uses_guide_token = true;
+    std::vector<llama_token> guide_tokens;
+
     llama_model *model = nullptr;
     float loading_progress = 0;
     bool is_load_interrupted = false;
@@ -92,6 +108,9 @@ struct llama_rn_context {
     llama_rn_context_mtmd *mtmd_wrapper = nullptr;
     bool has_multimodal = false;
 
+    llama_rn_context_vocoder *vocoder_wrapper = nullptr;
+    bool has_vocoder = false;
+
     ~llama_rn_context();
 
     void rewind();
@@ -104,7 +123,8 @@ struct llama_rn_context {
       const std::string &json_schema,
       const std::string &tools,
       const bool &parallel_tool_calls,
-      const std::string &tool_choice
+      const std::string &tool_choice,
+      const bool &enable_thinking
     ) const;
     std::string getFormattedChat(
       const std::string &messages,
@@ -112,12 +132,14 @@ struct llama_rn_context {
     ) const;
     void truncatePrompt(std::vector<llama_token> &prompt_tokens);
     void loadPrompt(const std::vector<std::string> &media_paths);
+    void setGuideTokens(const std::vector<llama_token> &tokens);
     void beginCompletion();
     void endCompletion();
     completion_token_output nextToken();
     size_t findStoppingStrings(const std::string &text, const size_t last_token_size, const stop_type type);
     completion_token_output doCompletion();
     std::vector<float> getEmbedding(common_params &embd_params);
+    std::vector<float> rerank(const std::string &query, const std::vector<std::string> &documents);
     std::string bench(int pp, int tg, int pl, int nr);
     int applyLoraAdapters(std::vector<common_adapter_lora_info> lora);
     void removeLoraAdapters();
@@ -137,6 +159,15 @@ struct llama_rn_context {
     );
 
     llama_rn_tokenize_result tokenize(const std::string &text, const std::vector<std::string> &media_paths);
+
+    // Vocoder methods
+    bool initVocoder(const std::string &vocoder_model_path);
+    tts_type getTTSType(json speaker = nullptr);
+    std::string getFormattedAudioCompletion(const std::string &speaker_json_str, const std::string &text_to_speak);
+    std::vector<llama_token> getAudioCompletionGuideTokens(const std::string &text_to_speak);
+    std::vector<float> decodeAudioTokens(const std::vector<llama_token> &tokens);
+    bool isVocoderEnabled() const;
+    void releaseVocoder();
 };
 
 // Logging macros

package/cpp/rn-tts.h

@@ -0,0 +1,39 @@
+
+
+namespace rnllama {
+
+// the default speaker profile is from: https://github.com/edwko/OuteTTS/blob/main/outetts/version/v1/default_speakers/en_male_1.json
+static const std::string default_audio_text = "<|text_start|>the<|text_sep|>overall<|text_sep|>package<|text_sep|>from<|text_sep|>just<|text_sep|>two<|text_sep|>people<|text_sep|>is<|text_sep|>pretty<|text_sep|>remarkable<|text_sep|>sure<|text_sep|>i<|text_sep|>have<|text_sep|>some<|text_sep|>critiques<|text_sep|>about<|text_sep|>some<|text_sep|>of<|text_sep|>the<|text_sep|>gameplay<|text_sep|>aspects<|text_sep|>but<|text_sep|>its<|text_sep|>still<|text_sep|>really<|text_sep|>enjoyable<|text_sep|>and<|text_sep|>it<|text_sep|>looks<|text_sep|>lovely<|text_sep|>";
+static const std::string default_audio_data = R"(<|audio_start|>
+the<|t_0.08|><|code_start|><|257|><|740|><|636|><|913|><|788|><|1703|><|code_end|>
+overall<|t_0.36|><|code_start|><|127|><|201|><|191|><|774|><|700|><|532|><|1056|><|557|><|798|><|298|><|1741|><|747|><|1662|><|1617|><|1702|><|1527|><|368|><|1588|><|1049|><|1008|><|1625|><|747|><|1576|><|728|><|1019|><|1696|><|1765|><|code_end|>
+package<|t_0.56|><|code_start|><|935|><|584|><|1319|><|627|><|1016|><|1491|><|1344|><|1117|><|1526|><|1040|><|239|><|1435|><|951|><|498|><|723|><|1180|><|535|><|789|><|1649|><|1637|><|78|><|465|><|1668|><|901|><|595|><|1675|><|117|><|1009|><|1667|><|320|><|840|><|79|><|507|><|1762|><|1508|><|1228|><|1768|><|802|><|1450|><|1457|><|232|><|639|><|code_end|>
+from<|t_0.19|><|code_start|><|604|><|782|><|1682|><|872|><|1532|><|1600|><|1036|><|1761|><|647|><|1554|><|1371|><|653|><|1595|><|950|><|code_end|>
+just<|t_0.25|><|code_start|><|1782|><|1670|><|317|><|786|><|1748|><|631|><|599|><|1155|><|1364|><|1524|><|36|><|1591|><|889|><|1535|><|541|><|440|><|1532|><|50|><|870|><|code_end|>
+two<|t_0.24|><|code_start|><|1681|><|1510|><|673|><|799|><|805|><|1342|><|330|><|519|><|62|><|640|><|1138|><|565|><|1552|><|1497|><|1552|><|572|><|1715|><|1732|><|code_end|>
+people<|t_0.39|><|code_start|><|593|><|274|><|136|><|740|><|691|><|633|><|1484|><|1061|><|1138|><|1485|><|344|><|428|><|397|><|1562|><|645|><|917|><|1035|><|1449|><|1669|><|487|><|442|><|1484|><|1329|><|1832|><|1704|><|600|><|761|><|653|><|269|><|code_end|>
+is<|t_0.16|><|code_start|><|566|><|583|><|1755|><|646|><|1337|><|709|><|802|><|1008|><|485|><|1583|><|652|><|10|><|code_end|>
+pretty<|t_0.32|><|code_start|><|1818|><|1747|><|692|><|733|><|1010|><|534|><|406|><|1697|><|1053|><|1521|><|1355|><|1274|><|816|><|1398|><|211|><|1218|><|817|><|1472|><|1703|><|686|><|13|><|822|><|445|><|1068|><|code_end|>
+remarkable<|t_0.68|><|code_start|><|230|><|1048|><|1705|><|355|><|706|><|1149|><|1535|><|1787|><|1356|><|1396|><|835|><|1583|><|486|><|1249|><|286|><|937|><|1076|><|1150|><|614|><|42|><|1058|><|705|><|681|><|798|><|934|><|490|><|514|><|1399|><|572|><|1446|><|1703|><|1346|><|1040|><|1426|><|1304|><|664|><|171|><|1530|><|625|><|64|><|1708|><|1830|><|1030|><|443|><|1509|><|1063|><|1605|><|1785|><|721|><|1440|><|923|><|code_end|>
+sure<|t_0.36|><|code_start|><|792|><|1780|><|923|><|1640|><|265|><|261|><|1525|><|567|><|1491|><|1250|><|1730|><|362|><|919|><|1766|><|543|><|1|><|333|><|113|><|970|><|252|><|1606|><|133|><|302|><|1810|><|1046|><|1190|><|1675|><|code_end|>
+i<|t_0.08|><|code_start|><|123|><|439|><|1074|><|705|><|1799|><|637|><|code_end|>
+have<|t_0.16|><|code_start|><|1509|><|599|><|518|><|1170|><|552|><|1029|><|1267|><|864|><|419|><|143|><|1061|><|0|><|code_end|>
+some<|t_0.16|><|code_start|><|619|><|400|><|1270|><|62|><|1370|><|1832|><|917|><|1661|><|167|><|269|><|1366|><|1508|><|code_end|>
+critiques<|t_0.60|><|code_start|><|559|><|584|><|1163|><|1129|><|1313|><|1728|><|721|><|1146|><|1093|><|577|><|928|><|27|><|630|><|1080|><|1346|><|1337|><|320|><|1382|><|1175|><|1682|><|1556|><|990|><|1683|><|860|><|1721|><|110|><|786|><|376|><|1085|><|756|><|1523|><|234|><|1334|><|1506|><|1578|><|659|><|612|><|1108|><|1466|><|1647|><|308|><|1470|><|746|><|556|><|1061|><|code_end|>
+about<|t_0.29|><|code_start|><|26|><|1649|><|545|><|1367|><|1263|><|1728|><|450|><|859|><|1434|><|497|><|1220|><|1285|><|179|><|755|><|1154|><|779|><|179|><|1229|><|1213|><|922|><|1774|><|1408|><|code_end|>
+some<|t_0.23|><|code_start|><|986|><|28|><|1649|><|778|><|858|><|1519|><|1|><|18|><|26|><|1042|><|1174|><|1309|><|1499|><|1712|><|1692|><|1516|><|1574|><|code_end|>
+of<|t_0.07|><|code_start|><|197|><|716|><|1039|><|1662|><|64|><|code_end|>
+the<|t_0.08|><|code_start|><|1811|><|1568|><|569|><|886|><|1025|><|1374|><|code_end|>
+gameplay<|t_0.48|><|code_start|><|1269|><|1092|><|933|><|1362|><|1762|><|1700|><|1675|><|215|><|781|><|1086|><|461|><|838|><|1022|><|759|><|649|><|1416|><|1004|><|551|><|909|><|787|><|343|><|830|><|1391|><|1040|><|1622|><|1779|><|1360|><|1231|><|1187|><|1317|><|76|><|997|><|989|><|978|><|737|><|189|><|code_end|>
+aspects<|t_0.56|><|code_start|><|1423|><|797|><|1316|><|1222|><|147|><|719|><|1347|><|386|><|1390|><|1558|><|154|><|440|><|634|><|592|><|1097|><|1718|><|712|><|763|><|1118|><|1721|><|1311|><|868|><|580|><|362|><|1435|><|868|><|247|><|221|><|886|><|1145|><|1274|><|1284|><|457|><|1043|><|1459|><|1818|><|62|><|599|><|1035|><|62|><|1649|><|778|><|code_end|>
+but<|t_0.20|><|code_start|><|780|><|1825|><|1681|><|1007|><|861|><|710|><|702|><|939|><|1669|><|1491|><|613|><|1739|><|823|><|1469|><|648|><|code_end|>
+its<|t_0.09|><|code_start|><|92|><|688|><|1623|><|962|><|1670|><|527|><|599|><|code_end|>
+still<|t_0.27|><|code_start|><|636|><|10|><|1217|><|344|><|713|><|957|><|823|><|154|><|1649|><|1286|><|508|><|214|><|1760|><|1250|><|456|><|1352|><|1368|><|921|><|615|><|5|><|code_end|>
+really<|t_0.36|><|code_start|><|55|><|420|><|1008|><|1659|><|27|><|644|><|1266|><|617|><|761|><|1712|><|109|><|1465|><|1587|><|503|><|1541|><|619|><|197|><|1019|><|817|><|269|><|377|><|362|><|1381|><|507|><|1488|><|4|><|1695|><|code_end|>
+enjoyable<|t_0.49|><|code_start|><|678|><|501|><|864|><|319|><|288|><|1472|><|1341|><|686|><|562|><|1463|><|619|><|1563|><|471|><|911|><|730|><|1811|><|1006|><|520|><|861|><|1274|><|125|><|1431|><|638|><|621|><|153|><|876|><|1770|><|437|><|987|><|1653|><|1109|><|898|><|1285|><|80|><|593|><|1709|><|843|><|code_end|>
+and<|t_0.15|><|code_start|><|1285|><|987|><|303|><|1037|><|730|><|1164|><|502|><|120|><|1737|><|1655|><|1318|><|code_end|>
+it<|t_0.09|><|code_start|><|848|><|1366|><|395|><|1601|><|1513|><|593|><|1302|><|code_end|>
+looks<|t_0.27|><|code_start|><|1281|><|1266|><|1755|><|572|><|248|><|1751|><|1257|><|695|><|1380|><|457|><|659|><|585|><|1315|><|1105|><|1776|><|736|><|24|><|736|><|654|><|1027|><|code_end|>
+lovely<|t_0.56|><|code_start|><|634|><|596|><|1766|><|1556|><|1306|><|1285|><|1481|><|1721|><|1123|><|438|><|1246|><|1251|><|795|><|659|><|1381|><|1658|><|217|><|1772|><|562|><|952|><|107|><|1129|><|1112|><|467|><|550|><|1079|><|840|><|1615|><|1469|><|1380|><|168|><|917|><|836|><|1827|><|437|><|583|><|67|><|595|><|1087|><|1646|><|1493|><|1677|><|code_end|>)";
+
+}

package/cpp/sampling.cpp

@@ -161,7 +161,7 @@ struct common_sampler * common_sampler_init(const struct llama_model * model, co
         LM_GGML_ABORT("llguidance (cmake -DLLAMA_LLGUIDANCE=ON) is not enabled");
 #endif // LLAMA_USE_LLGUIDANCE
     } else {
-        std::vector<std::string> patterns_at_start;
+        std::vector<std::string> trigger_patterns;
         std::vector<std::string> patterns_anywhere;
         std::vector<llama_token> trigger_tokens;
         for (const auto & trigger : params.grammar_triggers) {
@@ -173,10 +173,13 @@ struct common_sampler * common_sampler_init(const struct llama_model * model, co
                     break;
                 }
                 case COMMON_GRAMMAR_TRIGGER_TYPE_PATTERN:
-                case COMMON_GRAMMAR_TRIGGER_TYPE_PATTERN_START:
                 {
-                    const auto & pattern = trigger.value;
-                    (trigger.type == COMMON_GRAMMAR_TRIGGER_TYPE_PATTERN_START ? patterns_at_start : patterns_anywhere).push_back(pattern);
+                    patterns_anywhere.push_back(trigger.value);
+                    break;
+                }
+                case COMMON_GRAMMAR_TRIGGER_TYPE_PATTERN_FULL:
+                {
+                    trigger_patterns.push_back(trigger.value);
                     break;
                 }
                 case COMMON_GRAMMAR_TRIGGER_TYPE_TOKEN:
@@ -190,10 +193,6 @@ struct common_sampler * common_sampler_init(const struct llama_model * model, co
             }
         }
 
-        std::vector<std::string> trigger_patterns;
-        if (!patterns_at_start.empty()) {
-            trigger_patterns.push_back("^(" + string_join(patterns_at_start, "|") + ")[\\s\\S]*");
-        }
         if (!patterns_anywhere.empty()) {
             trigger_patterns.push_back("^[\\s\\S]*?(" + string_join(patterns_anywhere, "|") + ")[\\s\\S]*");
         }

package/cpp/tools/mtmd/clip-impl.h

@@ -107,6 +107,7 @@
 // ultravox
 #define TN_CONV1D       "a.conv1d.%d.%s"
 #define TN_MM_AUDIO_MLP "mm.a.mlp.%d.%s"
+#define TN_MM_AUDIO_FC  "mm.a.fc.%s" // fully connected layer
 #define TN_MM_NORM_PRE  "mm.a.norm_pre.%s"
 #define TN_MM_NORM_MID  "mm.a.norm_mid.%s"
 
@@ -128,6 +129,8 @@ enum projector_type {
     PROJECTOR_TYPE_ULTRAVOX,
     PROJECTOR_TYPE_INTERNVL,
     PROJECTOR_TYPE_LLAMA4,
+    PROJECTOR_TYPE_QWEN2A,
+    PROJECTOR_TYPE_QWEN25O, // will be replaced by QWEN2A or QWEN25VL depending on clip_ctx
     PROJECTOR_TYPE_UNKNOWN,
 };
 
@@ -145,6 +148,8 @@ static std::map<projector_type, std::string> PROJECTOR_TYPE_NAMES = {
     { PROJECTOR_TYPE_ULTRAVOX,  "ultravox"},
     { PROJECTOR_TYPE_INTERNVL,  "internvl"},
     { PROJECTOR_TYPE_LLAMA4,    "llama4"},
+    { PROJECTOR_TYPE_QWEN2A,    "qwen2a"},
+    { PROJECTOR_TYPE_QWEN25O,   "qwen2.5o"},
 };
 
 static projector_type clip_projector_type_from_string(const std::string & str) {