convert : add BPE pre-tokenization for DBRX (#7132)

* Add BPE pre-tokenization for DBRX.

* Add vocab GGUFs.

* Remove test.

* Remove GGUFs.

convert-hf-to-gguf-update.py

@@ -68,6 +68,7 @@ models = [
     {"name": "refact",         "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/smallcloudai/Refact-1_6-base", },
     {"name": "command-r",      "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/CohereForAI/c4ai-command-r-v01", },
     {"name": "olmo",           "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/allenai/OLMo-1.7-7B-hf", },
+    {"name": "dbrx",           "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/databricks/dbrx-base", },
 ]
 
 # make directory "models/tokenizers" if it doesn't exist
@@ -151,6 +152,8 @@ for model in models:
     # print the "pre_tokenizer" content from the tokenizer.json
     with open(f"models/tokenizers/{name}/tokenizer.json", "r", encoding="utf-8") as f:
         cfg = json.load(f)
+        normalizer = cfg["normalizer"]
+        logger.info("normalizer: " + json.dumps(normalizer, indent=4))
         pre_tokenizer = cfg["pre_tokenizer"]
         logger.info("pre_tokenizer: " + json.dumps(pre_tokenizer, indent=4))
 

convert-hf-to-gguf.py

@@ -317,6 +317,9 @@ class Model(ABC):
         if chkhsh == "b6dc8df998e1cfbdc4eac8243701a65afe638679230920b50d6f17d81c098166":
             # ref: https://huggingface.co/allenai/OLMo-1.7-7B-hf
             res = "olmo"
+        if chkhsh == "a8594e3edff7c29c003940395316294b2c623e09894deebbc65f33f1515df79e":
+            # ref: https://huggingface.co/databricks/dbrx-instruct
+            res = "dbrx"
 
         if res is None:
             logger.warning("\n")

examples/finetune/finetune.cpp

@@ -575,7 +575,7 @@ static struct ggml_tensor * llama_build_lora_finetune_graphs(
     GGML_ASSERT(tokens_input->type == GGML_TYPE_I32);
 
     auto add_to_f32 = [] (struct ggml_context * ctx, struct ggml_tensor * a, struct ggml_tensor * b) {
-        if (ggml_is_quantized(a->type) || a->type == GGML_TYPE_F16) {
+        if (ggml_is_quantized(a->type) || a->type == GGML_TYPE_F16 || a->type == GGML_TYPE_BF16) {
             return ggml_add_cast(ctx, a, b, GGML_TYPE_F32);
         } else if (a->type == GGML_TYPE_F32) {
             return ggml_add(ctx, a, b);

examples/quantize/quantize.cpp

@@ -46,7 +46,8 @@ static const std::vector<struct quant_option> QUANT_OPTIONS = {
     { "Q5_K_M", LLAMA_FTYPE_MOSTLY_Q5_K_M, " 4.45G, +0.0122 ppl @ LLaMA-v1-7B", },
     { "Q6_K",   LLAMA_FTYPE_MOSTLY_Q6_K,   " 5.15G, +0.0008 ppl @ LLaMA-v1-7B", },
     { "Q8_0",   LLAMA_FTYPE_MOSTLY_Q8_0,   " 6.70G, +0.0004 ppl @ LLaMA-v1-7B", },
-    { "F16",    LLAMA_FTYPE_MOSTLY_F16,    "13.00G              @ 7B", },
+    { "F16",    LLAMA_FTYPE_MOSTLY_F16,    "14.00G, -0.0020 ppl @ Mistral-7B", },
+    { "BF16",   LLAMA_FTYPE_MOSTLY_BF16,   "14.00G, -0.0050 ppl @ Mistral-7B", },
     { "F32",    LLAMA_FTYPE_ALL_F32,       "26.00G              @ 7B", },
     // Note: Ensure COPY comes after F32 to avoid ftype 0 from matching.
     { "COPY",   LLAMA_FTYPE_ALL_F32,       "only copy tensors, no quantizing", },

ggml-impl.h

@@ -17,6 +17,83 @@
 #define MIN(a, b) ((a) < (b) ? (a) : (b))
 #define MAX(a, b) ((a) > (b) ? (a) : (b))
 
+/**
+ * Converts brain16 to float32.
+ *
+ * The bfloat16 floating point format has the following structure:
+ *
+ *       ┌sign
+ *       │
+ *       │   ┌exponent
+ *       │   │
+ *       │   │      ┌mantissa
+ *       │   │      │
+ *       │┌──┴───┐┌─┴───┐
+ *     0b0000000000000000 brain16
+ *
+ * Since bf16 has the same number of exponent bits as a 32bit float,
+ * encoding and decoding numbers becomes relatively straightforward.
+ *
+ *       ┌sign
+ *       │
+ *       │   ┌exponent
+ *       │   │
+ *       │   │      ┌mantissa
+ *       │   │      │
+ *       │┌──┴───┐┌─┴───────────────────┐
+ *     0b00000000000000000000000000000000 IEEE binary32
+ *
+ * For comparison, the standard fp16 format has fewer exponent bits.
+ *
+ *       ┌sign
+ *       │
+ *       │  ┌exponent
+ *       │  │
+ *       │  │    ┌mantissa
+ *       │  │    │
+ *       │┌─┴─┐┌─┴──────┐
+ *     0b0000000000000000 IEEE binary16
+ *
+ * @see IEEE 754-2008
+ */
+static inline float ggml_compute_bf16_to_fp32(ggml_bf16_t h) {
+    union {
+        float f;
+        uint32_t i;
+    } u;
+    u.i = (uint32_t)h.bits << 16;
+    return u.f;
+}
+
+/**
+ * Converts float32 to brain16.
+ *
+ * This function is binary identical to AMD Zen4 VCVTNEPS2BF16.
+ * Subnormals shall be flushed to zero, and NANs will be quiet.
+ * This code should vectorize nicely if using modern compilers.
+ */
+static inline ggml_bf16_t ggml_compute_fp32_to_bf16(float s) {
+    ggml_bf16_t h;
+    union {
+        float f;
+        uint32_t i;
+    } u;
+    u.f = s;
+    if ((u.i & 0x7fffffff) > 0x7f800000) { /* nan */
+        h.bits = (u.i >> 16) | 64; /* force to quiet */
+        return h;
+    }
+    if (!(u.i & 0x7f800000)) { /* subnormal */
+        h.bits = (u.i & 0x80000000) >> 16; /* flush to zero */
+        return h;
+    }
+    h.bits = (u.i + (0x7fff + ((u.i >> 16) & 1))) >> 16;
+    return h;
+}
+
+#define GGML_FP32_TO_BF16(x) ggml_compute_fp32_to_bf16(x)
+#define GGML_BF16_TO_FP32(x) ggml_compute_bf16_to_fp32(x)
+
 #ifdef __cplusplus
 extern "C" {
 #endif

ggml-metal.m

@@ -803,7 +803,7 @@ static bool ggml_metal_supports_op(const struct ggml_metal_context * ctx, const
         case GGML_OP_DIAG_MASK_INF:
         case GGML_OP_GET_ROWS:
             {
-                return op->ne[3] == 1;
+                return op->src[0]->type != GGML_TYPE_BF16 && op->ne[3] == 1;
             }
         default:
             return false;

ggml-metal.metal

@@ -2175,7 +2175,7 @@ kernel void kernel_flash_attn_ext_f16(
 
     const short D4 = D/4;
     const short D8 = D/8;
-    const short Q8 = Q/8;
+  //const short Q8 = Q/8;
     const short NW = N_SIMDWIDTH;
     const short SH = (C + Q); // shared memory per simdgroup in (half)
 

ggml-quants.c

@@ -12450,6 +12450,24 @@ bool ggml_validate_row_data(enum ggml_type type, const void * data, size_t nbyte
     const size_t nb = nbytes/ggml_type_size(type);
 
     switch (type) {
+        case GGML_TYPE_BF16:
+            {
+                int nans = 0;
+                int infs = 0;
+                const unsigned short * f = (const unsigned short *) data;
+                for (size_t i = 0; i < nb; ++i) {
+                    nans += (f[i] & 0x7fff) > 0x7f80;
+                    infs += (f[i] & 0x7fff) == 0x7f80;
+                }
+                if (nans) {
+                    fprintf(stderr, "%s: found %d NaNs in row of %zu BF16 values\n", __func__, nans, nb);
+                    return false;
+                }
+                if (infs) {
+                    fprintf(stderr, "%s: found %d infinities in row of %zu BF16 values\n", __func__, infs, nb);
+                    return false;
+                }
+            } break;
         case GGML_TYPE_F16:
             {
                 const ggml_fp16_t * f = (const ggml_fp16_t *) data;

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;
+    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);
 
-    // 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);
+    // 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:

gguf-py/gguf/constants.py

@@ -817,6 +817,7 @@ class GGMLQuantizationType(IntEnum):
     I64     = 27
     F64     = 28
     IQ1_M   = 29
+    BF16    = 30
 
 
 class GGUFEndian(IntEnum):
@@ -888,6 +889,7 @@ GGML_QUANT_SIZES = {
     GGMLQuantizationType.I64:     (1, 8),
     GGMLQuantizationType.F64:     (1, 8),
     GGMLQuantizationType.IQ1_M:   (256, QK_K // 8 + QK_K // 16  + QK_K // 32),
+    GGMLQuantizationType.BF16:    (1, 2),
 }
 
 

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:
@@ -4392,6 +4394,9 @@ static void llm_load_vocab(
             } 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()));
             }
@@ -6129,6 +6134,7 @@ 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
             )
@@ -12197,6 +12203,7 @@ 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+",
@@ -14158,13 +14165,16 @@ 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 {
@@ -14173,7 +14183,14 @@ 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);
@@ -14192,6 +14209,8 @@ 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);
             }
@@ -14552,6 +14571,7 @@ 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

llama.h

@@ -82,6 +82,7 @@ extern "C" {
         LLAMA_VOCAB_PRE_TYPE_REFACT         = 8,
         LLAMA_VOCAB_PRE_TYPE_COMMAND_R      = 9,
         LLAMA_VOCAB_PRE_TYPE_OLMO           = 10,
+        LLAMA_VOCAB_PRE_TYPE_DBRX           = 11,
     };
 
     // note: these values should be synchronized with ggml_rope
@@ -137,6 +138,7 @@ 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
     };

scripts/compare-llama-bench.py

@@ -93,11 +93,14 @@ help_s = (
     "specified values are averaged WITHOUT weighing by the --repetitions parameter of llama-bench."
 )
 parser.add_argument("-s", "--show", help=help_s)
+parser.add_argument("--verbose", action="store_true", help="increase output verbosity")
 
 known_args, unknown_args = parser.parse_known_args()
 
+logging.basicConfig(level=logging.DEBUG if known_args.verbose else logging.INFO)
+
 if unknown_args:
-    logger.error(f"Received unknown args: {unknown_args}.")
+    logger.error(f"Received unknown args: {unknown_args}.\n")
     parser.print_help()
     sys.exit(1)
 
@@ -110,7 +113,7 @@ if input_file is None:
         input_file = sqlite_files[0]
 
 if input_file is None:
-    logger.error("Cannot find a suitable input file, please provide one.")
+    logger.error("Cannot find a suitable input file, please provide one.\n")
     parser.print_help()
     sys.exit(1)
 
@@ -202,12 +205,12 @@ elif repo is not None:
     hexsha8_baseline = find_parent_in_data(repo.heads.master.commit)
 
     if hexsha8_baseline is None:
-        logger.error("No baseline was provided and did not find data for any master branch commits.")
+        logger.error("No baseline was provided and did not find data for any master branch commits.\n")
         parser.print_help()
         sys.exit(1)
 else:
     logger.error("No baseline was provided and the current working directory "
-                 "is not part of a git repository from which a baseline could be inferred.")
+                 "is not part of a git repository from which a baseline could be inferred.\n")
     parser.print_help()
     sys.exit(1)
 
@@ -238,7 +241,7 @@ elif repo is not None:
             break
 
     if hexsha8_compare is None:
-        logger.error("No compare target was provided and did not find data for any non-master commits.")
+        logger.error("No compare target was provided and did not find data for any non-master commits.\n")
         parser.print_help()
         sys.exit(1)
 else:
@@ -361,7 +364,7 @@ if "gpu_info" in show:
 headers  = [PRETTY_NAMES[p] for p in show]
 headers += ["Test", f"t/s {name_baseline}", f"t/s {name_compare}", "Speedup"]
 
-logger.info(tabulate(
+print(tabulate( # noqa: NP100
     table,
     headers=headers,
     floatfmt=".2f",

tests/test-backend-ops.cpp

@@ -50,7 +50,7 @@ static void init_tensor_uniform(ggml_tensor * tensor, float min = -1.0f, float m
 
     if (tensor->type == GGML_TYPE_F32 || tensor->type == GGML_TYPE_I32) {
         ggml_backend_tensor_set(tensor, data.data(), 0, size * sizeof(float));
-    } else if (ggml_is_quantized(tensor->type) || tensor->type == GGML_TYPE_F16) {
+    } else if (ggml_is_quantized(tensor->type) || tensor->type == GGML_TYPE_F16 || tensor->type == GGML_TYPE_BF16) {
         GGML_ASSERT(size % ggml_blck_size(tensor->type) == 0);
         std::vector<uint8_t> dataq(ggml_row_size(tensor->type, size));
         std::vector<float> imatrix(tensor->ne[0], 1.0f); // dummy importance matrix
@@ -92,6 +92,8 @@ static std::vector<float> tensor_to_float(const ggml_tensor * t) {
                     size_t i = i3*t->nb[3] + i2*t->nb[2] + i1*t->nb[1] + i0/bs*t->nb[0];
                     if (t->type == GGML_TYPE_F16) {
                         tv.push_back(ggml_fp16_to_fp32(*(ggml_fp16_t*)&buf[i]));
+                    } else if (t->type == GGML_TYPE_BF16) {
+                        tv.push_back(ggml_bf16_to_fp32(*(ggml_bf16_t*)&buf[i]));
                     } else if (t->type == GGML_TYPE_F32) {
                         tv.push_back(*(float *) &buf[i]);
                     } else if (t->type == GGML_TYPE_I32) {
@@ -1898,7 +1900,7 @@ static bool test_backend(ggml_backend_t backend, test_mode mode, const char * op
     std::default_random_engine rng(0);
 
     const ggml_type all_types[] = {
-        GGML_TYPE_F32, GGML_TYPE_F16,
+        GGML_TYPE_F32, GGML_TYPE_F16, GGML_TYPE_BF16,
         GGML_TYPE_Q4_0, GGML_TYPE_Q4_1,
         GGML_TYPE_Q5_0, GGML_TYPE_Q5_1,
         GGML_TYPE_Q8_0,