llama_cpp 0.15.0 → 0.15.1

data/vendor/tmp/llama.cpp/ggml.h

@@ -326,14 +326,20 @@ extern "C" {
     // get ggml_status name string
     GGML_API GGML_CALL const char * ggml_status_to_string(enum ggml_status status);
 
+    // ieee 754-2008 half-precision float16
+    // todo: make this not an integral type
     typedef uint16_t ggml_fp16_t;
-
-    // convert FP16 <-> FP32
-    GGML_API float       ggml_fp16_to_fp32(ggml_fp16_t x);
-    GGML_API ggml_fp16_t ggml_fp32_to_fp16(float x);
-
-    GGML_API void ggml_fp16_to_fp32_row(const ggml_fp16_t * x, float * y, int64_t n);
-    GGML_API void ggml_fp32_to_fp16_row(const float * x, ggml_fp16_t * y, int64_t n);
+    GGML_API float       ggml_fp16_to_fp32(ggml_fp16_t);
+    GGML_API ggml_fp16_t ggml_fp32_to_fp16(float);
+    GGML_API void        ggml_fp16_to_fp32_row(const ggml_fp16_t *, float *, int64_t);
+    GGML_API void        ggml_fp32_to_fp16_row(const float *, ggml_fp16_t *, int64_t);
+
+    // google brain half-precision bfloat16
+    typedef struct { uint16_t bits; } ggml_bf16_t;
+    GGML_API ggml_bf16_t ggml_fp32_to_bf16(float);
+    GGML_API float       ggml_bf16_to_fp32(ggml_bf16_t);  // consider just doing << 16
+    GGML_API void        ggml_bf16_to_fp32_row(const ggml_bf16_t *, float *, int64_t);
+    GGML_API void        ggml_fp32_to_bf16_row(const float *, ggml_bf16_t *, int64_t);
 
     struct ggml_object;
     struct ggml_context;
@@ -370,6 +376,7 @@ extern "C" {
         GGML_TYPE_I64     = 27,
         GGML_TYPE_F64     = 28,
         GGML_TYPE_IQ1_M   = 29,
+        GGML_TYPE_BF16    = 30,
         GGML_TYPE_COUNT,
     };
 
@@ -410,6 +417,7 @@ extern "C" {
         GGML_FTYPE_MOSTLY_IQ2_S   = 21, // except 1d tensors
         GGML_FTYPE_MOSTLY_IQ4_XS  = 22, // except 1d tensors
         GGML_FTYPE_MOSTLY_IQ1_M   = 23, // except 1d tensors
+        GGML_FTYPE_MOSTLY_BF16    = 24, // except 1d tensors
     };
 
     // available tensor operations:

data/vendor/tmp/llama.cpp/llama.cpp

@@ -3175,6 +3175,7 @@ struct llama_model_loader {
             switch (type_max) {
                 case GGML_TYPE_F32:     ftype = LLAMA_FTYPE_ALL_F32;        break;
                 case GGML_TYPE_F16:     ftype = LLAMA_FTYPE_MOSTLY_F16;     break;
+                case GGML_TYPE_BF16:    ftype = LLAMA_FTYPE_MOSTLY_BF16;    break;
                 case GGML_TYPE_Q4_0:    ftype = LLAMA_FTYPE_MOSTLY_Q4_0;    break;
                 case GGML_TYPE_Q4_1:    ftype = LLAMA_FTYPE_MOSTLY_Q4_1;    break;
                 case GGML_TYPE_Q5_0:    ftype = LLAMA_FTYPE_MOSTLY_Q5_0;    break;
@@ -3666,6 +3667,7 @@ static std::string llama_model_ftype_name(llama_ftype ftype) {
     switch (ftype) {
         case LLAMA_FTYPE_ALL_F32:     return "all F32";
         case LLAMA_FTYPE_MOSTLY_F16:  return "F16";
+        case LLAMA_FTYPE_MOSTLY_BF16: return "BF16";
         case LLAMA_FTYPE_MOSTLY_Q4_0: return "Q4_0";
         case LLAMA_FTYPE_MOSTLY_Q4_1: return "Q4_1";
         case LLAMA_FTYPE_MOSTLY_Q4_1_SOME_F16:
@@ -4383,6 +4385,21 @@ static void llm_load_vocab(
             } else if (
                     tokenizer_pre == "gpt-2") {
                 vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_GPT2;
+            } else if (
+                    tokenizer_pre == "refact") {
+                vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_REFACT;
+            } else if (
+                tokenizer_pre == "command-r") {
+                vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_COMMAND_R;
+            } else if (
+                tokenizer_pre == "qwen2") {
+                vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_QWEN2;
+            } else if (
+                tokenizer_pre == "olmo") {
+                vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_OLMO;
+            } else if (
+                tokenizer_pre == "dbrx") {
+                vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_DBRX;
             } else {
                 throw std::runtime_error(format("unknown pre-tokenizer type: '%s'", tokenizer_pre.c_str()));
             }
@@ -6120,6 +6137,7 @@ static int llama_model_load(const std::string & fname, llama_model & model, llam
             || !(
                 model.ftype == LLAMA_FTYPE_ALL_F32 ||
                 model.ftype == LLAMA_FTYPE_MOSTLY_F16 ||
+                model.ftype == LLAMA_FTYPE_MOSTLY_BF16 ||
                 model.ftype == LLAMA_FTYPE_MOSTLY_Q4_0 ||
                 model.ftype == LLAMA_FTYPE_MOSTLY_Q4_1
             )
@@ -11952,7 +11970,7 @@ static bool llama_is_user_defined_token(const llama_vocab& vocab, llama_token id
 static uint8_t llama_token_to_byte(const llama_vocab& vocab, llama_token id) {
     GGML_ASSERT(llama_vocab_get_type(vocab) != LLAMA_VOCAB_TYPE_NONE);
     GGML_ASSERT(llama_is_byte_token(vocab, id));
-    const auto& token_data = vocab.id_to_token.at(id);
+    const auto & token_data = vocab.id_to_token.at(id);
     switch (llama_vocab_get_type(vocab)) {
         case LLAMA_VOCAB_TYPE_SPM: {
             auto buf = token_data.text.substr(3, 2);
@@ -12188,6 +12206,7 @@ struct llm_tokenizer_bpe {
             case LLAMA_VOCAB_TYPE_BPE:
                 switch (vocab.type_pre) {
                     case LLAMA_VOCAB_PRE_TYPE_LLAMA3:
+                    case LLAMA_VOCAB_PRE_TYPE_DBRX:
                         word_collection = unicode_regex_split(text, {
                             // original regex from tokenizer.json
                             //"(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}{1,3}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
@@ -12212,14 +12231,13 @@ struct llm_tokenizer_bpe {
                             "\\s?\\p{L}+",
                             "\\s?\\p{P}+",
                             "[一-龥ࠀ-一가-퟿]+",
-                            "\\p{N}+",
+                            "\\p{N}",
                         });
                         break;
                     case LLAMA_VOCAB_PRE_TYPE_FALCON:
                         word_collection = unicode_regex_split(text, {
                             "[\\p{P}\\$\\+<=>\\^~\\|]+",
                             "'s|'t|'re|'ve|'m|'ll|'d| ?\\p{L}+| ?\\p{N}+| ?[^\\s\\p{L}\\p{N}]+|\\s+(?!\\S)",
-                            "\\p{N}+",
                             "[0-9][0-9][0-9]",
                         });
                         break;
@@ -12235,11 +12253,26 @@ struct llm_tokenizer_bpe {
                         });
                         break;
                     case LLAMA_VOCAB_PRE_TYPE_STARCODER:
+                    case LLAMA_VOCAB_PRE_TYPE_REFACT:
+                    case LLAMA_VOCAB_PRE_TYPE_COMMAND_R:
+                        word_collection = unicode_regex_split(text, {
+                            "\\p{N}",
+                            "'s|'t|'re|'ve|'m|'ll|'d| ?\\p{L}+| ?\\p{N}+| ?[^\\s\\p{L}\\p{N}]+|\\s+(?!\\S)",
+                        });
+                        break;
                     case LLAMA_VOCAB_PRE_TYPE_GPT2:
+                    case LLAMA_VOCAB_PRE_TYPE_OLMO:
                         word_collection = unicode_regex_split(text, {
                             "'s|'t|'re|'ve|'m|'ll|'d| ?\\p{L}+| ?\\p{N}+| ?[^\\s\\p{L}\\p{N}]+|\\s+(?!\\S)",
                         });
                         break;
+                    case LLAMA_VOCAB_PRE_TYPE_QWEN2:
+                        word_collection = unicode_regex_split(text, {
+                            // original regex from tokenizer.json
+                            // "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+"
+                            "(?:'[sS]|'[tT]|'[rR][eE]|'[vV][eE]|'[mM]|'[lL][lL]|'[dD])|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+                        });
+                        break;
                     default:
                         // default regex for BPE tokenization pre-processing
                         word_collection = unicode_regex_split(text, {
@@ -12455,7 +12488,7 @@ struct llm_tokenizer_wpm {
                 continue;
             }
             code = unicode_tolower(code);
-            if (type == CODEPOINT_TYPE_WHITESPACE) {
+            if (type == CODEPOINT_TYPE_SEPARATOR) {
                 code = ' ';
             }
             std::string s = unicode_cpt_to_utf8(code);
@@ -14142,13 +14175,16 @@ static void llama_tensor_dequantize_internal(
         if (qtype.to_float == NULL) {
             throw std::runtime_error(format("type %s unsupported for integer quantization: no dequantization available", ggml_type_name(tensor->type)));
         }
-    } else if (tensor->type != GGML_TYPE_F16) {
+    } else if (tensor->type != GGML_TYPE_F16 &&
+               tensor->type != GGML_TYPE_BF16) {
         throw std::runtime_error(format("cannot dequantize/convert tensor type %s", ggml_type_name(tensor->type)));
     }
 
     if (nthread < 2) {
         if (tensor->type == GGML_TYPE_F16) {
             ggml_fp16_to_fp32_row((ggml_fp16_t *)tensor->data, f32_output, nelements);
+        } else if (tensor->type == GGML_TYPE_BF16) {
+            ggml_bf16_to_fp32_row((ggml_bf16_t *)tensor->data, f32_output, nelements);
         } else if (ggml_is_quantized(tensor->type)) {
             qtype.to_float(tensor->data, f32_output, nelements);
         } else {
@@ -14157,7 +14193,14 @@ static void llama_tensor_dequantize_internal(
         return;
     }
 
-    size_t block_size = tensor->type == GGML_TYPE_F16 ? 1 : (size_t)ggml_blck_size(tensor->type);
+    size_t block_size;
+    if (tensor->type == GGML_TYPE_F16 ||
+        tensor->type == GGML_TYPE_BF16) {
+        block_size = 1;
+    } else {
+        block_size = (size_t)ggml_blck_size(tensor->type);
+    }
+
     size_t block_size_bytes = ggml_type_size(tensor->type);
 
     GGML_ASSERT(nelements % block_size == 0);
@@ -14176,6 +14219,8 @@ static void llama_tensor_dequantize_internal(
         auto compute = [qtype] (ggml_type typ, uint8_t * inbuf, float * outbuf, int nels) {
             if (typ == GGML_TYPE_F16) {
                 ggml_fp16_to_fp32_row((ggml_fp16_t *)inbuf, outbuf, nels);
+            } else if (typ == GGML_TYPE_BF16) {
+                ggml_bf16_to_fp32_row((ggml_bf16_t *)inbuf, outbuf, nels);
             } else {
                 qtype.to_float(inbuf, outbuf, nels);
             }
@@ -14536,6 +14581,7 @@ static void llama_model_quantize_internal(const std::string & fname_inp, const s
         case LLAMA_FTYPE_MOSTLY_Q5_1: default_type = GGML_TYPE_Q5_1; break;
         case LLAMA_FTYPE_MOSTLY_Q8_0: default_type = GGML_TYPE_Q8_0; break;
         case LLAMA_FTYPE_MOSTLY_F16:  default_type = GGML_TYPE_F16;  break;
+        case LLAMA_FTYPE_MOSTLY_BF16: default_type = GGML_TYPE_BF16; break;
         case LLAMA_FTYPE_ALL_F32:     default_type = GGML_TYPE_F32;  break;
 
         // K-quants
@@ -15473,13 +15519,6 @@ struct llama_context * llama_new_context_with_model(
         cparams.flash_attn = false;
     }
 
-#ifdef GGML_USE_HIPBLAS
-    if (cparams.flash_attn) {
-        LLAMA_LOG_WARN("%s: flash_attn is not yet compatible with HIPBLAS builds - forcing off\n", __func__);
-        cparams.flash_attn = false;
-    }
-#endif
-
     if (params.seed == LLAMA_DEFAULT_SEED) {
         params.seed = time(NULL);
     }
@@ -17466,9 +17505,10 @@ int32_t llama_tokenize(
 
 static std::string llama_decode_text(const std::string & text) {
     std::string decoded_text;
-    auto unicode_sequences = unicode_cpts_from_utf8(text);
-    for (auto & unicode_sequence : unicode_sequences) {
-        decoded_text += unicode_utf8_to_byte(unicode_cpt_to_utf8(unicode_sequence));
+
+    const auto cpts = unicode_cpts_from_utf8(text);
+    for (const auto cpt : cpts) {
+        decoded_text += unicode_utf8_to_byte(unicode_cpt_to_utf8(cpt));
     }
 
     return decoded_text;
@@ -17832,7 +17872,7 @@ struct llama_timings llama_get_timings(struct llama_context * ctx) {
         /*.t_eval_ms   =*/ 1e-3 * ctx->t_eval_us,
 
         /*.n_sample =*/ std::max(1, ctx->n_sample),
-        /*.n_p_eval =*/ std::max(1, ctx->n_p_eval),
+        /*.n_p_eval =*/ std::max(0, ctx->n_p_eval),
         /*.n_eval   =*/ std::max(1, ctx->n_eval),
     };
 

data/vendor/tmp/llama.cpp/llama.h

@@ -79,6 +79,11 @@ extern "C" {
         LLAMA_VOCAB_PRE_TYPE_MPT            = 5,
         LLAMA_VOCAB_PRE_TYPE_STARCODER      = 6,
         LLAMA_VOCAB_PRE_TYPE_GPT2           = 7,
+        LLAMA_VOCAB_PRE_TYPE_REFACT         = 8,
+        LLAMA_VOCAB_PRE_TYPE_COMMAND_R      = 9,
+        LLAMA_VOCAB_PRE_TYPE_QWEN2          = 10,
+        LLAMA_VOCAB_PRE_TYPE_OLMO           = 11,
+        LLAMA_VOCAB_PRE_TYPE_DBRX           = 12,
     };
 
     // note: these values should be synchronized with ggml_rope
@@ -134,6 +139,7 @@ extern "C" {
         LLAMA_FTYPE_MOSTLY_IQ2_M         = 29, // except 1d tensors
         LLAMA_FTYPE_MOSTLY_IQ4_XS        = 30, // except 1d tensors
         LLAMA_FTYPE_MOSTLY_IQ1_M         = 31, // except 1d tensors
+        LLAMA_FTYPE_MOSTLY_BF16          = 32, // except 1d tensors
 
         LLAMA_FTYPE_GUESSED = 1024, // not specified in the model file
     };
@@ -171,7 +177,7 @@ extern "C" {
         bool sorted;
     } llama_token_data_array;
 
-    typedef bool (*llama_progress_callback)(float progress, void *ctx);
+    typedef bool (*llama_progress_callback)(float progress, void * user_data);
 
     // Input data for llama_decode
     // A llama_batch object can contain input about one or many sequences

data/vendor/tmp/llama.cpp/sgemm.cpp

@@ -1,6 +1,3 @@
-// -*- mode:c++;indent-tabs-mode:nil;c-basic-offset:4;coding:utf-8 -*-
-// vi: set et ft=c++ ts=4 sts=4 sw=4 fenc=utf-8 :vi
-//
 // Copyright 2024 Mozilla Foundation
 //
 // Permission is hereby granted, free of charge, to any person obtaining
@@ -585,15 +582,15 @@ class tinyBLAS_Q0_ARM {
 };
 #endif // __ARM_FEATURE_DOTPROD
 
-#if defined(__AVX2__) || defined(__AVX512F__)
+#if defined(__AVX2__) || defined(__AVX512F__) || defined(__AVX__)
 template <typename TA, typename TB, typename TC>
-class tinyBLAS_Q0_AVX2 {
+class tinyBLAS_Q0_AVX {
   public:
-    tinyBLAS_Q0_AVX2(int64_t k,
-                     const TA *A, int64_t lda,
-                     const TB *B, int64_t ldb,
-                     TC *C, int64_t ldc,
-                     int ith, int nth)
+    tinyBLAS_Q0_AVX(int64_t k,
+                    const TA *A, int64_t lda,
+                    const TB *B, int64_t ldb,
+                    TC *C, int64_t ldc,
+                    int ith, int nth)
         : A(A), B(B), C(C), k(k), lda(lda), ldb(ldb), ldc(ldc), ith(ith), nth(nth) {
     }
 
@@ -728,14 +725,34 @@ class tinyBLAS_Q0_AVX2 {
             __m256 Cv[RN][RM] = {};
             for (int64_t l = 0; l < k; ++l)
                 for (int64_t j = 0; j < RN; ++j)
-                    for (int64_t i = 0; i < RM; ++i)
+                    for (int64_t i = 0; i < RM; ++i) {
+#if defined(__AVX2__)
+                        __m256 udTmp = updot(_mm256_sign_epi8(load(A + lda * (ii + i) + l),
+                                                              load(A + lda * (ii + i) + l)),
+                                             _mm256_sign_epi8(load(B + ldb * (jj + j) + l),
+                                                              load(A + lda * (ii + i) + l)));
+#else
+                        __m128i ali0 = load0(A + lda * (ii + i) + l);
+                        __m128i ali1 = load1(A + lda * (ii + i) + l);
+                        __m128i blj0 = load0(B + ldb * (jj + j) + l);
+                        __m128i blj1 = load1(B + ldb * (jj + j) + l);
+
+                        __m128i sepAA0 = _mm_sign_epi8(ali0, ali0);
+                        __m128i sepAA1 = _mm_sign_epi8(ali1, ali1);
+                        __m128i sepBA0 = _mm_sign_epi8(blj0, ali0);
+                        __m128i sepBA1 = _mm_sign_epi8(blj1, ali1);
+
+                        // updot
+                        const __m128i oneFill = _mm_set1_epi16(1);
+                        __m128i mad0 = _mm_maddubs_epi16(sepAA0, sepBA0);
+                        __m128i mad1 = _mm_maddubs_epi16(sepAA1, sepBA1);
+                        __m256 udTmp = _mm256_cvtepi32_ps(MM256_SET_M128I(_mm_madd_epi16(oneFill, mad1), _mm_madd_epi16(oneFill, mad0)));
+#endif
                         Cv[j][i] = madd(_mm256_set1_ps(unhalf(A[lda * (ii + i) + l].d) *
                                                        unhalf(B[ldb * (jj + j) + l].d)),
-                                        updot(_mm256_sign_epi8(load(A + lda * (ii + i) + l),
-                                                               load(A + lda * (ii + i) + l)),
-                                              _mm256_sign_epi8(load(B + ldb * (jj + j) + l),
-                                                               load(A + lda * (ii + i) + l))),
-                                        Cv[j][i]);
+                                                       udTmp,
+                                                       Cv[j][i]);
+                    }
             for (int64_t j = 0; j < RN; ++j)
                 for (int64_t i = 0; i < RM; ++i)
                     C[ldc * (jj + j) + (ii + i)] = hsum(Cv[j][i]);
@@ -746,10 +763,28 @@ class tinyBLAS_Q0_AVX2 {
         return _mm256_loadu_si256((const __m256i *)b->qs);
     }
 
+    inline __m128i load0(const block_q8_0 *b) {
+        return _mm_loadu_si128((const __m128i *)b->qs);
+    }
+
+    inline __m128i load1(const block_q8_0 *b) {
+        return _mm_loadu_si128(((const __m128i *)b->qs) + 1);
+    }
+
     inline __m256i load(const block_q4_0 *b) {
         return _mm256_sub_epi8(denibble(b->qs), _mm256_set1_epi8(8));
     }
 
+    inline __m128i load0(const block_q4_0 *b) {
+        const __m128i x = _mm_loadu_si128((const __m128i *)(b->qs));
+        return _mm_sub_epi8(_mm_and_si128(_mm_set1_epi8(15), x), _mm_set1_epi8(8));
+    }
+
+    inline __m128i load1(const block_q4_0 *b) {
+        const __m128i x = _mm_loadu_si128((const __m128i *)(b->qs));
+        return _mm_sub_epi8(_mm_and_si128(_mm_set1_epi8(15), _mm_srli_epi16(x, 4)), _mm_set1_epi8(8));
+    }
+
     inline __m256 updot(__m256i u, __m256i s) {
         __m256i res;
 #if defined(__AVXVNNI__) || (defined(__AVX512VNNI__) && defined(__AVX512VL__))
@@ -777,7 +812,7 @@ class tinyBLAS_Q0_AVX2 {
     const int ith;
     const int nth;
 };
-#endif // __AVX2__
+#endif // __AVX__
 
 } // namespace
 
@@ -928,8 +963,8 @@ bool llamafile_sgemm(int64_t m, int64_t n, int64_t k, const void *A, int64_t lda
     case GGML_TYPE_Q8_0: {
         if (Btype != GGML_TYPE_Q8_0)
            return false;
-#if defined(__AVX2__) || defined(__AVX512F__)
-        tinyBLAS_Q0_AVX2<block_q8_0, block_q8_0, float> tb{
+#if defined(__AVX2__) || defined(__AVX512F__) || defined(__AVX__)
+        tinyBLAS_Q0_AVX<block_q8_0, block_q8_0, float> tb{
             k, (const block_q8_0 *)A, lda,
             (const block_q8_0 *)B, ldb,
             (float *)C, ldc,
@@ -952,8 +987,8 @@ bool llamafile_sgemm(int64_t m, int64_t n, int64_t k, const void *A, int64_t lda
     case GGML_TYPE_Q4_0: {
         if (Btype != GGML_TYPE_Q8_0)
             return false;
-#if defined(__AVX2__) || defined(__AVX512F__)
-        tinyBLAS_Q0_AVX2<block_q4_0, block_q8_0, float> tb{
+#if defined(__AVX2__) || defined(__AVX512F__) || defined(__AVX__)
+        tinyBLAS_Q0_AVX<block_q4_0, block_q8_0, float> tb{
             k, (const block_q4_0 *)A, lda,
             (const block_q8_0 *)B, ldb,
             (float *)C, ldc,