gguf : read / write sample models

examples/gguf/gguf.cpp

@@ -1,15 +1,326 @@
 #include "ggml.h"
 
 #include <cstdio>
+#include <cinttypes>
 #include <string>
+#include <sstream>
+#include <fstream>
+#include <vector>
 
-bool gguf_write(const std::string & fname) {
+enum gguf_type {
+    GGUF_TYPE_UINT8   = 0,
+    GGUF_TYPE_INT8    = 1,
+    GGUF_TYPE_UINT16  = 2,
+    GGUF_TYPE_INT16   = 3,
+    GGUF_TYPE_UINT32  = 4,
+    GGUF_TYPE_INT32   = 5,
+    GGUF_TYPE_FLOAT32 = 6,
+    GGUF_TYPE_BOOL    = 7,
+    GGUF_TYPE_STRING  = 8,
+    GGUF_TYPE_ARRAY   = 9,
+};
 
+template<typename T>
+static std::string to_string(const T & val) {
+    std::stringstream ss;
+    ss << val;
+    return ss.str();
+}
+
+void gguf_ex_write_str(std::ofstream & fout, const std::string & val) {
+    const int32_t n = val.size();
+    fout.write((const char *) &n, sizeof(n));
+    fout.write(val.c_str(), n);
+}
+
+void gguf_ex_write_i32(std::ofstream & fout, int32_t val) {
+    fout.write((const char *) &val, sizeof(val));
+}
+
+void gguf_ex_write_u64(std::ofstream & fout, size_t val) {
+    fout.write((const char *) &val, sizeof(val));
+}
+
+template<typename T>
+void gguf_ex_write_param(std::ofstream & fout, const std::string & key, enum gguf_type type, const T & val) {
+    gguf_ex_write_str(fout, key);
+    fout.write((const char *) &type, sizeof(type));
+    fout.write((const char *) &val,  sizeof(val));
+
+    fprintf(stdout, "%s: write param: %s = %s\n", __func__, key.c_str(), to_string(val).c_str());
+}
+
+template<>
+void gguf_ex_write_param<std::string>(std::ofstream & fout, const std::string & key, enum gguf_type type, const std::string & val) {
+    gguf_ex_write_str(fout, key);
+    fout.write((const char *) &type, sizeof(type));
+
+    const int32_t n = val.size();
+    fout.write((const char *) &n, sizeof(n));
+    fout.write(val.c_str(), n);
+}
+
+bool gguf_ex_write(const std::string & fname) {
+    std::ofstream fout(fname.c_str(), std::ios::binary);
+
+    {
+        const int32_t magic = GGUF_MAGIC;
+        fout.write((const char *) &magic, sizeof(magic));
+    }
+
+    {
+        const int32_t version = GGUF_VERSION;
+        fout.write((const char *) &version, sizeof(version));
+    }
+
+    const int n_tensors = 10;
+    const int n_kv = 9;
+
+    fout.write((const char*) &n_tensors, sizeof(n_tensors));
+    fout.write((const char*) &n_kv, sizeof(n_kv));
+
+    fprintf(stdout, "%s: write header\n", __func__);
+
+    // kv data
+    {
+        gguf_ex_write_param< uint8_t>(fout, "some.parameter.uint8",   GGUF_TYPE_UINT8,   0x12);
+        gguf_ex_write_param<  int8_t>(fout, "some.parameter.int8",    GGUF_TYPE_INT8,   -0x13);
+        gguf_ex_write_param<uint16_t>(fout, "some.parameter.uint16",  GGUF_TYPE_UINT16,  0x1234);
+        gguf_ex_write_param< int16_t>(fout, "some.parameter.int16",   GGUF_TYPE_INT16,  -0x1235);
+        gguf_ex_write_param<uint32_t>(fout, "some.parameter.uint32",  GGUF_TYPE_UINT32,  0x12345678);
+        gguf_ex_write_param< int32_t>(fout, "some.parameter.int32",   GGUF_TYPE_INT32,  -0x12345679);
+
+        gguf_ex_write_param<float>   (fout, "some.parameter.float32", GGUF_TYPE_FLOAT32, 0.123456789f);
+        gguf_ex_write_param<bool>    (fout, "some.parameter.bool",    GGUF_TYPE_BOOL,    true);
+
+        gguf_ex_write_param<std::string>(fout, "some.parameter.string",  GGUF_TYPE_STRING,  "hello world");
+    }
+
+    uint64_t offset_tensor = 0;
+
+    struct ggml_init_params params = {
+        /*.mem_size   =*/ 128ull*1024ull*1024ull,
+        /*.mem_buffer =*/ NULL,
+        /*.no_alloc   =*/ false,
+    };
+
+    struct ggml_context * ctx_data = ggml_init(params);
+
+    // tensor infos
+    for (int i = 0; i < n_tensors; ++i) {
+        const std::string name = "tensor_" + to_string(i);
+
+        int64_t ne[GGML_MAX_DIMS] = { 1 };
+        int32_t n_dims = rand() % GGML_MAX_DIMS + 1;
+
+        for (int j = 0; j < n_dims; ++j) {
+            ne[j] = rand() % 10 + 1;
+        }
+
+        struct ggml_tensor * cur = ggml_new_tensor(ctx_data, GGML_TYPE_F32, n_dims, ne);
+        ggml_set_name(cur, name.c_str());
+
+        {
+            float * data = (float *) cur->data;
+            for (int j = 0; j < ggml_nelements(cur); ++j) {
+                data[j] = 100 + i;
+            }
+        }
+
+        fprintf(stdout, "%s: tensor: %s, %d dims, ne = [", __func__, name.c_str(), n_dims);
+        for (int j = 0; j < 4; ++j) {
+            fprintf(stdout, "%s%3d", j == 0 ? "" : ", ", (int) cur->ne[j]);
+        }
+        fprintf(stdout, "], offset_tensor = %6" PRIu64 "\n", offset_tensor);
+
+        gguf_ex_write_str(fout, name);
+        gguf_ex_write_i32(fout, n_dims);
+        for (int j = 0; j < n_dims; ++j) {
+            gguf_ex_write_i32(fout, cur->ne[j]);
+        }
+        gguf_ex_write_i32(fout, cur->type);
+        gguf_ex_write_u64(fout, offset_tensor);
+
+        offset_tensor += GGML_PAD(ggml_nbytes(cur), GGUF_DEFAULT_ALIGNMENT);
+    }
+
+    const uint64_t offset_data = GGML_PAD((uint64_t) fout.tellp(), GGUF_DEFAULT_ALIGNMENT);
+
+    fprintf(stdout, "%s: data offset = %" PRIu64 "\n", __func__, offset_data);
+
+    {
+        const size_t pad = offset_data - fout.tellp();
+
+        for (size_t j = 0; j < pad; ++j) {
+            fout.put(0);
+        }
+    }
+
+    for (int i = 0; i < n_tensors; ++i) {
+        fprintf(stdout, "%s: writing tensor %d data\n", __func__, i);
+
+        const std::string name = "tensor_" + to_string(i);
+
+        struct ggml_tensor * cur = ggml_get_tensor(ctx_data, name.c_str());
+
+        fout.write((const char *) cur->data, ggml_nbytes(cur));
+
+        {
+            const size_t pad = GGML_PAD(ggml_nbytes(cur), GGUF_DEFAULT_ALIGNMENT) - ggml_nbytes(cur);
+
+            for (size_t j = 0; j < pad; ++j) {
+                fout.put(0);
+            }
+        }
+    }
+
+    fout.close();
+
+    fprintf(stdout, "%s: wrote file '%s;\n", __func__, fname.c_str());
+
+    ggml_free(ctx_data);
 
     return true;
 }
 
-bool gguf_read(const std::string & fname) {
+// just read tensor info
+bool gguf_ex_read_0(const std::string & fname) {
+    struct gguf_init_params params = {
+        /*.no_alloc = */ false,
+        /*.ctx      = */ NULL,
+    };
+
+    struct gguf_context * ctx = gguf_init_from_file(fname.c_str(), params);
+
+    fprintf(stdout, "%s: version:      %d\n", __func__, gguf_get_version(ctx));
+    fprintf(stdout, "%s: alignment:   %zu\n", __func__, gguf_get_alignment(ctx));
+    fprintf(stdout, "%s: data offset: %zu\n", __func__, gguf_get_data_offset(ctx));
+
+    // kv
+    {
+        const int n_kv = gguf_get_n_kv(ctx);
+
+        fprintf(stdout, "%s: n_kv: %d\n", __func__, n_kv);
+
+        for (int i = 0; i < n_kv; ++i) {
+            const char * key = gguf_get_key(ctx, i);
+
+            fprintf(stdout, "%s: kv[%d]: key = %s\n", __func__, i, key);
+        }
+    }
+
+    // tensor info
+    {
+        const int n_tensors = gguf_get_n_tensors(ctx);
+
+        fprintf(stdout, "%s: n_tensors: %d\n", __func__, n_tensors);
+
+        for (int i = 0; i < n_tensors; ++i) {
+            const char * name = gguf_get_tensor_name(ctx, i);
+            const size_t offset = gguf_get_tensor_offset(ctx, i);
+
+            fprintf(stdout, "%s: tensor[%d]: name = %s, offset = %zu\n", __func__, i, name, offset);
+        }
+    }
+
+    return true;
+}
+
+// read and create ggml_context containing the tensors and their data
+bool gguf_ex_read_1(const std::string & fname) {
+    struct ggml_context * ctx_data = NULL;
+
+    struct gguf_init_params params = {
+        /*.no_alloc = */ false,
+        /*.ctx      = */ &ctx_data,
+    };
+
+    struct gguf_context * ctx = gguf_init_from_file(fname.c_str(), params);
+
+    fprintf(stdout, "%s: version:      %d\n", __func__, gguf_get_version(ctx));
+    fprintf(stdout, "%s: alignment:   %zu\n", __func__, gguf_get_alignment(ctx));
+    fprintf(stdout, "%s: data offset: %zu\n", __func__, gguf_get_data_offset(ctx));
+
+    // kv
+    {
+        const int n_kv = gguf_get_n_kv(ctx);
+
+        fprintf(stdout, "%s: n_kv: %d\n", __func__, n_kv);
+
+        for (int i = 0; i < n_kv; ++i) {
+            const char * key = gguf_get_key(ctx, i);
+
+            fprintf(stdout, "%s: kv[%d]: key = %s\n", __func__, i, key);
+        }
+    }
+
+    // tensor info
+    {
+        const int n_tensors = gguf_get_n_tensors(ctx);
+
+        fprintf(stdout, "%s: n_tensors: %d\n", __func__, n_tensors);
+
+        for (int i = 0; i < n_tensors; ++i) {
+            const char * name = gguf_get_tensor_name(ctx, i);
+            const size_t offset = gguf_get_tensor_offset(ctx, i);
+
+            fprintf(stdout, "%s: tensor[%d]: name = %s, offset = %zu\n", __func__, i, name, offset);
+        }
+    }
+
+    // data
+    {
+        const int n_tensors = gguf_get_n_tensors(ctx);
+
+        for (int i = 0; i < n_tensors; ++i) {
+            fprintf(stdout, "%s: reading tensor %d data\n", __func__, i);
+
+            const std::string name = "tensor_" + to_string(i);
+
+            struct ggml_tensor * cur = ggml_get_tensor(ctx_data, name.c_str());
+
+            fprintf(stdout, "%s: tensor[%d]: n_dims = %d, name = %s, data = %p\n",
+                    __func__, i, cur->n_dims, cur->name, cur->data);
+
+            // check data
+            {
+                const float * data = (const float *) cur->data;
+                for (int j = 0; j < ggml_nelements(cur); ++j) {
+                    if (data[j] != 100 + i) {
+                        fprintf(stderr, "%s: tensor[%d]: data[%d] = %f\n", __func__, i, j, data[j]);
+                        return false;
+                    }
+                }
+            }
+        }
+    }
+
+    fprintf(stdout, "%s: ctx_data size: %zu\n", __func__, ggml_get_mem_size(ctx_data));
+
+    ggml_free(ctx_data);
+    gguf_free(ctx);
+
+    return true;
+}
+
+// read just the tensor info and mmap the data in user code
+bool gguf_ex_read_2(const std::string & fname) {
+    struct ggml_context * ctx_data = NULL;
+
+    struct gguf_init_params params = {
+        /*.no_alloc = */ true,
+        /*.ctx      = */ &ctx_data,
+    };
+
+    struct gguf_context * ctx = gguf_init_from_file(fname.c_str(), params);
+
+    // TODO: mmap based on tensor infos
+
+    fprintf(stdout, "%s: ctx_data size: %zu\n", __func__, ggml_get_mem_size(ctx_data));
+
+    ggml_free(ctx_data);
+    gguf_free(ctx);
+
     return true;
 }
 
@@ -20,14 +331,16 @@ int main(int argc, char ** argv) {
     }
 
     const std::string fname(argv[1]);
-    const std::string mode(argv[2]);
+    const std::string mode (argv[2]);
 
     GGML_ASSERT((mode == "r" || mode == "w") && "mode must be r or w");
 
     if (mode == "w") {
-        GGML_ASSERT(gguf_write(fname) && "failed to write gguf file");
+        GGML_ASSERT(gguf_ex_write(fname) && "failed to write gguf file");
     } else if (mode == "r") {
-        GGML_ASSERT(gguf_read(fname)  && "failed to read gguf file");
+        GGML_ASSERT(gguf_ex_read_0(fname) && "failed to read gguf file");
+        GGML_ASSERT(gguf_ex_read_1(fname) && "failed to read gguf file");
+        GGML_ASSERT(gguf_ex_read_2(fname) && "failed to read gguf file");
     }
 
     return 0;

ggml.c

@@ -18364,7 +18364,7 @@ struct gguf_tensor_info {
 
     enum ggml_type type;
 
-    uint64_t offset; // offset from beginning of file, must be a multiple of `ALIGNMENT`
+    uint64_t offset; // offset from start of `data`, must be a multiple of `ALIGNMENT`
 };
 
 struct gguf_context {
@@ -18385,9 +18385,7 @@ static bool gguf_fread_el(void * dst, size_t size, FILE * file, size_t * offset)
     return n == size;
 }
 
-static bool gguf_fread_str(void * dst, FILE * file, size_t * offset) {
+static bool gguf_fread_str(struct gguf_str * p, FILE * file, size_t * offset) {
-    struct gguf_str * p = (struct gguf_str *) dst;
-
     p->n    = 0;
     p->data = NULL;
 
@@ -18395,14 +18393,12 @@ static bool gguf_fread_str(void * dst, FILE * file, size_t * offset) {
 
     // TODO: how to avoid mallocs for strings?
     ok = ok && gguf_fread_el(&p->n,    sizeof(p->n), file, offset); p->data = calloc(p->n + 1, 1);
-    ok = ok && gguf_fread_el(&p->data, p->n,         file, offset);
+    ok = ok && gguf_fread_el( p->data, p->n,         file, offset);
 
     return ok;
 }
 
-struct gguf_context * gguf_init(const char * fname, struct gguf_init_params params) {
+struct gguf_context * gguf_init_from_file(const char * fname, struct gguf_init_params params) {
-    GGML_ASSERT(!params.load || params.malloc || params.ctx != NULL);
-
     FILE * file = fopen(fname, "rb");
     if (!file) {
         return NULL;
@@ -18446,10 +18442,14 @@ struct gguf_context * gguf_init(const char * fname, struct gguf_init_params para
     for (uint32_t i = 0; i < ctx->header.n_kv; ++i) {
         struct gguf_kv * kv = &ctx->header.kv[i];
 
+        //fprintf(stderr, "%s: reading kv %d\n", __func__, i);
+
         ok = ok && gguf_fread_str(&kv->key,                          file, &offset);
       //ok = ok && gguf_fread_el (&kv->n_bytes, sizeof(kv->n_bytes), file, &offset);
         ok = ok && gguf_fread_el (&kv->type,    sizeof(kv->type),    file, &offset);
 
+        //fprintf(stderr, "%s: reading kv with key %s\n", __func__, kv->key.data);
+
         switch (kv->type) {
             case GGUF_TYPE_UINT8:   ok = ok && gguf_fread_el (&kv->value.uint8,   sizeof(kv->value.uint8),   file, &offset); break;
             case GGUF_TYPE_INT8:    ok = ok && gguf_fread_el (&kv->value.int8,    sizeof(kv->value.int8),    file, &offset); break;
@@ -18464,6 +18464,10 @@ struct gguf_context * gguf_init(const char * fname, struct gguf_init_params para
                                     GGML_ASSERT("gguf: array type not implemented");
                                     break;
         };
+
+        if (!ok) {
+            break;
+        }
     }
 
     if (!ok) {
@@ -18478,12 +18482,14 @@ struct gguf_context * gguf_init(const char * fname, struct gguf_init_params para
     for (uint32_t i = 0; i < ctx->header.n_tensors; ++i) {
         struct gguf_tensor_info * info = &ctx->infos[i];
 
-        memset(info->ne, 1, sizeof(info->ne));
+        for (int j = 0; j < GGML_MAX_DIMS; ++j) {
+            info->ne[j] = 1;
+        }
 
         ok = ok && gguf_fread_str(&info->name,                          file, &offset);
         ok = ok && gguf_fread_el (&info->n_dims, sizeof(info->n_dims),  file, &offset);
         for (uint32_t j = 0; j < info->n_dims; ++j) {
-            ok = ok && gguf_fread_el (&info->ne[j], sizeof(info->ne[j]), file, &offset);
+            ok = ok && gguf_fread_el(&info->ne[j], sizeof(info->ne[j]), file, &offset);
         }
       //ok = ok && gguf_fread_el (&info->n_elms, sizeof(info->n_elms),  file, &offset);
         ok = ok && gguf_fread_el (&info->type,    sizeof(info->type),   file, &offset);
@@ -18536,28 +18542,30 @@ struct gguf_context * gguf_init(const char * fname, struct gguf_init_params para
         ctx->size_data += GGML_PAD(size_cur, ctx->alignment);
     }
 
+    // load the tensor data
     // TODO: simplify
-    if (params.load) {
+    if (params.ctx != NULL) {
-        if (params.malloc) {
-            ctx->data = GGML_ALIGNED_MALLOC(ctx->size_data);
-            fseek(file, ctx->offset, SEEK_SET);
-            ok = ok && gguf_fread_el(ctx->data, ctx->size_data, file, &offset);
-        } else {
         const size_t mem_size =
-                ctx->header.n_tensors*ggml_tensor_overhead() + 1 +
+            params.no_alloc ?
-                ctx->size_data;
+            (ctx->header.n_tensors + 1)*ggml_tensor_overhead() :
+            (ctx->header.n_tensors + 1)*ggml_tensor_overhead() + ctx->size_data;
 
         struct ggml_init_params pdata = {
             .mem_size   = mem_size,
             .mem_buffer = NULL,
-                .no_alloc   = false,
+            .no_alloc   = params.no_alloc,
         };
 
         *params.ctx = ggml_init(pdata);
 
         struct ggml_context * ctx_data = *params.ctx;
 
-            struct ggml_tensor * data = ggml_new_tensor_1d(ctx_data, GGML_TYPE_I8, ctx->size_data);
+        struct ggml_tensor * data = NULL;
+
+        if (params.no_alloc == false) {
+            data = ggml_new_tensor_1d(ctx_data, GGML_TYPE_I8, ctx->size_data);
+
+            ok = ok && data != NULL;
 
             // read the tensor data
             ok = ok && gguf_fread_el(data->data, ctx->size_data, file, &offset);
@@ -18571,10 +18579,11 @@ struct gguf_context * gguf_init(const char * fname, struct gguf_init_params para
             }
 
             ctx->data = data->data;
+        }
 
-            // create the tensors
         ggml_set_no_alloc(ctx_data, true);
 
+        // create the tensors
         for (uint32_t i = 0; i < ctx->header.n_tensors; ++i) {
             const int64_t ne[GGML_MAX_DIMS] = {
                 ctx->infos[i].ne[0],
@@ -18587,11 +18596,16 @@ struct gguf_context * gguf_init(const char * fname, struct gguf_init_params para
 
             ok = ok && cur != NULL;
 
+            ggml_set_name(cur, ctx->infos[i].name.data);
+
             if (!ok) {
                 break;
             }
 
-                cur->data = (char *) data->data + ctx->infos[i].offset - ctx->offset;
+            if (params.no_alloc == false) {
+              //cur->data = (char *) data->data + ctx->infos[i].offset - ctx->offset; // offset from start of file
+                cur->data = (char *) data->data + ctx->infos[i].offset;               // offset from data
+            }
         }
 
         if (!ok) {
@@ -18602,8 +18616,7 @@ struct gguf_context * gguf_init(const char * fname, struct gguf_init_params para
             return NULL;
         }
 
-            ggml_set_no_alloc(ctx_data, false);
+        ggml_set_no_alloc(ctx_data, params.no_alloc);
-        }
     }
 
     if (!ok) {

ggml.h

@@ -1622,10 +1622,9 @@ extern "C" {
     struct gguf_context;
 
     struct gguf_init_params {
-        bool load;   // load the tensor data
+        bool no_alloc;
-        bool malloc; // if false, create a ggml_context and allocate the tensor data in it
-                     // if  true, use malloc to allocate the tensor data instead
 
+        // if not NULL, create a ggml_context and allocate the tensor data in it
         struct ggml_context ** ctx;
     };