android : fix utf8 decoding error (#5935)

* examples: fix utf8 decoding error

some models have a tokenizer that decodes an id into an incomplete utf8 sequence, need to validate and wait for next token
one example would be: https://huggingface.co/Qwen/Qwen1.5-1.8B-Chat-GGUF/resolve/main/qwen1_5-1_8b-chat-q4_0.gguf and and an example of the token is 18137

* android : minor

---------

Co-authored-by: zhangfuwen <zhangfuwen@foxmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

README.md

@@ -8,11 +8,6 @@
 
 Inference of Meta's [LLaMA](https://arxiv.org/abs/2302.13971) model (and others) in pure C/C++
 
-> [!IMPORTANT]
-> **Quantization blind testing: https://github.com/ggerganov/llama.cpp/discussions/5962**
->
-> Vote for which quantization type provides better responses, all other parameters being the same.
-
 ### Recent API changes
 
 - [2024 Mar 8] `llama_kv_cache_seq_rm()` returns a `bool` instead of `void`, and new `llama_n_max_seq()` returns the upper limit of acceptable `seq_id` in batches (relevant when dealing with multiple sequences) https://github.com/ggerganov/llama.cpp/pull/5328
@@ -21,6 +16,8 @@ Inference of Meta's [LLaMA](https://arxiv.org/abs/2302.13971) model (and others)
 
 ### Hot topics
 
+- Looking for contributions to add Deepseek support: https://github.com/ggerganov/llama.cpp/issues/5981
+- Quantization blind testing: https://github.com/ggerganov/llama.cpp/discussions/5962
 - Initial Mamba support has been added: https://github.com/ggerganov/llama.cpp/pull/5328
 
 ----

examples/llama.android/app/src/main/cpp/llama-android.cpp

@@ -33,6 +33,45 @@ jclass la_int_var;
 jmethodID la_int_var_value;
 jmethodID la_int_var_inc;
 
+std::string cached_token_chars;
+
+bool is_valid_utf8(const char * string) {
+    if (!string) {
+        return true;
+    }
+
+    const unsigned char * bytes = (const unsigned char *)string;
+    int num;
+
+    while (*bytes != 0x00) {
+        if ((*bytes & 0x80) == 0x00) {
+            // U+0000 to U+007F
+            num = 1;
+        } else if ((*bytes & 0xE0) == 0xC0) {
+            // U+0080 to U+07FF
+            num = 2;
+        } else if ((*bytes & 0xF0) == 0xE0) {
+            // U+0800 to U+FFFF
+            num = 3;
+        } else if ((*bytes & 0xF8) == 0xF0) {
+            // U+10000 to U+10FFFF
+            num = 4;
+        } else {
+            return false;
+        }
+
+        bytes += 1;
+        for (int i = 1; i < num; ++i) {
+            if ((*bytes & 0xC0) != 0x80) {
+                return false;
+            }
+            bytes += 1;
+        }
+    }
+
+    return true;
+}
+
 static void log_callback(ggml_log_level level, const char * fmt, void * data) {
     if (level == GGML_LOG_LEVEL_ERROR)     __android_log_print(ANDROID_LOG_ERROR, TAG, fmt, data);
     else if (level == GGML_LOG_LEVEL_INFO) __android_log_print(ANDROID_LOG_INFO, TAG, fmt, data);
@@ -295,6 +334,8 @@ Java_com_example_llama_Llm_completion_1init(
         jint n_len
     ) {
 
+    cached_token_chars.clear();
+
     const auto text = env->GetStringUTFChars(jtext, 0);
     const auto context = reinterpret_cast<llama_context *>(context_pointer);
     const auto batch = reinterpret_cast<llama_batch *>(batch_pointer);
@@ -372,8 +413,16 @@ Java_com_example_llama_Llm_completion_1loop(
     }
 
     auto new_token_chars = llama_token_to_piece(context, new_token_id);
-    LOGi("new_token_chars: `%s`", new_token_chars.c_str());
-    auto new_token = env->NewStringUTF(new_token_chars.c_str());
+    cached_token_chars += new_token_chars;
+
+    jstring new_token = nullptr;
+    if (is_valid_utf8(cached_token_chars.c_str())) {
+        new_token = env->NewStringUTF(cached_token_chars.c_str());
+        LOGi("cached: %s, new_token_chars: `%s`, id: %d", cached_token_chars.c_str(), new_token_chars.c_str(), new_token_id);
+        cached_token_chars.clear();
+    } else {
+        new_token = env->NewStringUTF("");
+    }
 
     llama_batch_clear(*batch);
     llama_batch_add(*batch, new_token_id, n_cur, { 0 }, true);

examples/llama.android/app/src/main/java/com/example/llama/Llm.kt

@@ -71,7 +71,7 @@ class Llm {
         batch: Long,
         nLen: Int,
         ncur: IntVar
-    ): String
+    ): String?
 
     private external fun kv_cache_clear(context: Long)
 
@@ -115,7 +115,7 @@ class Llm {
                 val ncur = IntVar(completion_init(state.context, state.batch, message, nlen))
                 while (ncur.value <= nlen) {
                     val str = completion_loop(state.context, state.batch, nlen, ncur)
-                    if (str.isEmpty()) {
+                    if (str == null) {
                         break
                     }
                     emit(str)

ggml-quants.c

@@ -9009,8 +9009,8 @@ void ggml_vec_dot_iq2_s_q8_K(int n, float * restrict s, size_t bs, const void *
 
     static const uint8_t k_mask2[16] = {0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80, 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80,};
 
-    const uint8x16x2_t mask1 = vld1q_u8_x2(k_mask1);
-    const uint8x16_t   mask2 = vld1q_u8(k_mask2);
+    const ggml_uint8x16x2_t mask1 = ggml_vld1q_u8_x2(k_mask1);
+    const uint8x16_t        mask2 = vld1q_u8(k_mask2);
     const uint8x16_t m1 = vdupq_n_u8(1);
     const int32x4_t vzero = vdupq_n_s32(0);
 
@@ -9354,11 +9354,12 @@ void ggml_vec_dot_iq3_s_q8_K (int n, float * restrict s, size_t bs, const void *
 
     static const int16_t k_shift[8] = {8, 7, 6, 5, 4, 3, 2, 1};
 
-    const uint8x16x2_t mask1  = vld1q_u8_x2(k_mask1);
-    const uint8x16_t   mask2  = vld1q_u8(k_mask2);
-    const int16x8_t    hshift = vld1q_s16(k_shift);
-    const uint16x8_t   m256   = vdupq_n_u16(256);
-    const uint8x16_t   m1     = vdupq_n_u8(1);
+    const ggml_uint8x16x2_t mask1 = ggml_vld1q_u8_x2(k_mask1);
+    const uint8x16_t        mask2 = vld1q_u8(k_mask2);
+
+    const int16x8_t  hshift = vld1q_s16(k_shift);
+    const uint16x8_t m256   = vdupq_n_u16(256);
+    const uint8x16_t m1     = vdupq_n_u8(1);
 
     uint8x16x2_t vs;
     ggml_int8x16x4_t q3s;

scripts/sync-ggml.last

@@ -1 +1 @@
-8695910a39102609073d0e099aa7c97d6bcb3bf9
+43a6d4af1971ee2912ff7bc2404011ff327b6a60