@fugood/llama.node 0.2.2 → 0.3.0

package/src/llama.cpp/examples/gbnf-validator/CMakeLists.txt

@@ -1,5 +1,5 @@
-set(TARGET gbnf-validator)
+set(TARGET llama-gbnf-validator)
 add_executable(${TARGET} gbnf-validator.cpp)
 install(TARGETS ${TARGET} RUNTIME)
-target_link_libraries(${TARGET} PRIVATE common grammar-parser llama ${CMAKE_THREAD_LIBS_INIT})
+target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
 target_compile_features(${TARGET} PRIVATE cxx_std_11)

package/src/llama.cpp/examples/gbnf-validator/gbnf-validator.cpp

@@ -7,6 +7,8 @@
 
 #include <cstdio>
 #include <cstdlib>
+#include <sstream>
+#include <fstream>
 #include <string>
 #include <vector>
 
@@ -14,20 +16,25 @@ static bool llama_sample_grammar_string(struct llama_grammar * grammar, const st
     auto decoded = decode_utf8(input_str, {});
     const auto & code_points = decoded.first;
 
+    const llama_grammar_rules  & rules      = llama_grammar_get_rules (grammar);
+          llama_grammar_stacks & cur_stacks = llama_grammar_get_stacks(grammar);
+
     size_t pos = 0;
     for (auto it = code_points.begin(), end = code_points.end() - 1; it != end; ++it) {
-        auto prev_stacks = grammar->stacks;
-        llama_grammar_accept(grammar->rules, prev_stacks, *it, grammar->stacks);
-        if (grammar->stacks.empty()) {
+        const llama_grammar_stacks prev_stacks = llama_grammar_get_stacks(grammar); // copy
+
+        llama_grammar_accept(rules, prev_stacks, *it, cur_stacks);
+
+        if (cur_stacks.empty()) {
             error_pos = pos;
             error_msg = "Unexpected character '" + unicode_cpt_to_utf8(*it) + "'";
-            grammar->stacks = prev_stacks;
+            cur_stacks = prev_stacks;
             return false;
         }
         ++pos;
     }
 
-    for (const auto & stack : grammar->stacks) {
+    for (const auto & stack : cur_stacks) {
         if (stack.empty()) {
             return true;
         }
@@ -69,13 +76,14 @@ int main(int argc, char** argv) {
         return 1;
     }
 
-    fseek(grammar_file, 0, SEEK_END);
-    size_t grammar_size = ftell(grammar_file);
-    fseek(grammar_file, 0, SEEK_SET);
-
-    std::string grammar_str(grammar_size, ' ');
-    fread(&grammar_str[0], 1, grammar_size, grammar_file);
-    fclose(grammar_file);
+    std::string grammar_str;
+    {
+        std::ifstream grammar_file(grammar_filename);
+        GGML_ASSERT(grammar_file.is_open() && "Failed to open grammar file");
+        std::stringstream buffer;
+        buffer << grammar_file.rdbuf();
+        grammar_str = buffer.str();
+    }
 
     // Parse the GBNF grammar
     auto parsed_grammar = grammar_parser::parse(grammar_str.c_str());
@@ -98,22 +106,19 @@ int main(int argc, char** argv) {
     auto grammar = llama_grammar_init(
             grammar_rules.data(),
             grammar_rules.size(), parsed_grammar.symbol_ids.at("root"));
-
+    if (grammar == nullptr) {
+        throw std::runtime_error("Failed to initialize llama_grammar");
+    }
     // Read the input file
-    FILE* input_file = fopen(input_filename.c_str(), "r");
-    if (!input_file) {
-        fprintf(stdout, "Failed to open input file: %s\n", input_filename.c_str());
-        return 1;
+    std::string input_str;
+    {
+        std::ifstream input_file(input_filename);
+        GGML_ASSERT(input_file.is_open() && "Failed to open input file");
+        std::stringstream buffer;
+        buffer << input_file.rdbuf();
+        input_str = buffer.str();
     }
 
-    fseek(input_file, 0, SEEK_END);
-    size_t input_size = ftell(input_file);
-    fseek(input_file, 0, SEEK_SET);
-
-    std::string input_str(input_size, ' ');
-    fread(&input_str[0], 1, input_size, input_file);
-    fclose(input_file);
-
     // Validate the input string against the grammar
     size_t error_pos;
     std::string error_msg;

package/src/llama.cpp/examples/gguf/CMakeLists.txt

@@ -1,4 +1,4 @@
-set(TARGET gguf)
+set(TARGET llama-gguf)
 add_executable(${TARGET} gguf.cpp)
 install(TARGETS ${TARGET} RUNTIME)
 target_link_libraries(${TARGET} PRIVATE ggml ${CMAKE_THREAD_LIBS_INIT})

package/src/llama.cpp/examples/gguf/gguf.cpp

@@ -92,6 +92,11 @@ static bool gguf_ex_read_0(const std::string & fname) {
 
     struct gguf_context * ctx = gguf_init_from_file(fname.c_str(), params);
 
+    if (!ctx) {
+        fprintf(stderr, "%s: failed to load '%s'\n", __func__, fname.c_str());
+        return false;
+    }
+
     printf("%s: version:      %d\n", __func__, gguf_get_version(ctx));
     printf("%s: alignment:   %zu\n", __func__, gguf_get_alignment(ctx));
     printf("%s: data offset: %zu\n", __func__, gguf_get_data_offset(ctx));

package/src/llama.cpp/examples/gguf-hash/CMakeLists.txt

@@ -0,0 +1,15 @@
+set(TARGET llama-gguf-hash)
+add_executable(${TARGET} gguf-hash.cpp)
+install(TARGETS ${TARGET} RUNTIME)
+
+# clibs dependencies
+include_directories(deps/)
+add_library(xxhash OBJECT deps/xxhash/xxhash.c deps/xxhash/xxhash.h)
+target_link_libraries(${TARGET} PRIVATE xxhash)
+add_library(sha1 OBJECT deps/sha1/sha1.c deps/sha1/sha1.h)
+target_link_libraries(${TARGET} PRIVATE sha1)
+add_library(sha256 OBJECT deps/sha256/sha256.c deps/sha256/sha256.h)
+target_link_libraries(${TARGET} PRIVATE sha256)
+
+target_link_libraries(${TARGET} PRIVATE ggml ${CMAKE_THREAD_LIBS_INIT})
+target_compile_features(${TARGET} PRIVATE cxx_std_11)

package/src/llama.cpp/examples/gguf-hash/deps/rotate-bits/rotate-bits.h

@@ -0,0 +1,46 @@
+
+
+#ifndef __ROTATE_DEFS_H
+#define __ROTATE_DEFS_H
+
+#ifdef _MSC_VER
+
+#include <stdlib.h>
+
+#define ROTL32(v, n) _rotl((v), (n))
+#define ROTL64(v, n) _rotl64((v), (n))
+
+#define ROTR32(v, n) _rotr((v), (n))
+#define ROTR64(v, n) _rotr64((v), (n))
+
+#else
+
+#include <stdint.h>
+
+#define U8V(v) ((uint8_t)(v) & 0xFFU)
+#define U16V(v) ((uint16_t)(v) & 0xFFFFU)
+#define U32V(v) ((uint32_t)(v) & 0xFFFFFFFFU)
+#define U64V(v) ((uint64_t)(v) & 0xFFFFFFFFFFFFFFFFU)
+
+#define ROTL32(v, n) \
+  (U32V((uint32_t)(v) << (n)) | ((uint32_t)(v) >> (32 - (n))))
+
+// tests fail if we don't have this cast...
+#define ROTL64(v, n) \
+  (U64V((uint64_t)(v) << (n)) | ((uint64_t)(v) >> (64 - (n))))
+
+#define ROTR32(v, n) ROTL32(v, 32 - (n))
+#define ROTR64(v, n) ROTL64(v, 64 - (n))
+
+#endif
+
+#define ROTL8(v, n) \
+  (U8V((uint8_t)(v) << (n)) | ((uint8_t)(v) >> (8 - (n))))
+
+#define ROTL16(v, n) \
+  (U16V((uint16_t)(v) << (n)) | ((uint16_t)(v) >> (16 - (n))))
+
+#define ROTR8(v, n) ROTL8(v, 8 - (n))
+#define ROTR16(v, n) ROTL16(v, 16 - (n))
+
+#endif

package/src/llama.cpp/examples/gguf-hash/deps/sha1/sha1.c

@@ -0,0 +1,295 @@
+/*
+SHA-1 in C
+By Steve Reid <steve@edmweb.com>
+100% Public Domain
+
+Test Vectors (from FIPS PUB 180-1)
+"abc"
+  A9993E36 4706816A BA3E2571 7850C26C 9CD0D89D
+"abcdbcdecdefdefgefghfghighijhijkijkljklmklmnlmnomnopnopq"
+  84983E44 1C3BD26E BAAE4AA1 F95129E5 E54670F1
+A million repetitions of "a"
+  34AA973C D4C4DAA4 F61EEB2B DBAD2731 6534016F
+*/
+
+/* #define LITTLE_ENDIAN * This should be #define'd already, if true. */
+/* #define SHA1HANDSOFF * Copies data before messing with it. */
+
+#define SHA1HANDSOFF
+
+#include <stdio.h>
+#include <string.h>
+
+/* for uint32_t */
+#include <stdint.h>
+
+#include "sha1.h"
+
+
+#define rol(value, bits) (((value) << (bits)) | ((value) >> (32 - (bits))))
+
+/* blk0() and blk() perform the initial expand. */
+/* I got the idea of expanding during the round function from SSLeay */
+#if BYTE_ORDER == LITTLE_ENDIAN
+#define blk0(i) (block->l[i] = (rol(block->l[i],24)&0xFF00FF00) \
+    |(rol(block->l[i],8)&0x00FF00FF))
+#elif BYTE_ORDER == BIG_ENDIAN
+#define blk0(i) block->l[i]
+#else
+#error "Endianness not defined!"
+#endif
+#define blk(i) (block->l[i&15] = rol(block->l[(i+13)&15]^block->l[(i+8)&15] \
+    ^block->l[(i+2)&15]^block->l[i&15],1))
+
+/* (R0+R1), R2, R3, R4 are the different operations used in SHA1 */
+#define R0(v,w,x,y,z,i) z+=((w&(x^y))^y)+blk0(i)+0x5A827999+rol(v,5);w=rol(w,30);
+#define R1(v,w,x,y,z,i) z+=((w&(x^y))^y)+blk(i)+0x5A827999+rol(v,5);w=rol(w,30);
+#define R2(v,w,x,y,z,i) z+=(w^x^y)+blk(i)+0x6ED9EBA1+rol(v,5);w=rol(w,30);
+#define R3(v,w,x,y,z,i) z+=(((w|x)&y)|(w&x))+blk(i)+0x8F1BBCDC+rol(v,5);w=rol(w,30);
+#define R4(v,w,x,y,z,i) z+=(w^x^y)+blk(i)+0xCA62C1D6+rol(v,5);w=rol(w,30);
+
+
+/* Hash a single 512-bit block. This is the core of the algorithm. */
+
+void SHA1Transform(
+    uint32_t state[5],
+    const unsigned char buffer[64]
+)
+{
+    uint32_t a, b, c, d, e;
+
+    typedef union
+    {
+        unsigned char c[64];
+        uint32_t l[16];
+    } CHAR64LONG16;
+
+#ifdef SHA1HANDSOFF
+    CHAR64LONG16 block[1];      /* use array to appear as a pointer */
+
+    memcpy(block, buffer, 64);
+#else
+    /* The following had better never be used because it causes the
+     * pointer-to-const buffer to be cast into a pointer to non-const.
+     * And the result is written through.  I threw a "const" in, hoping
+     * this will cause a diagnostic.
+     */
+    CHAR64LONG16 *block = (const CHAR64LONG16 *) buffer;
+#endif
+    /* Copy context->state[] to working vars */
+    a = state[0];
+    b = state[1];
+    c = state[2];
+    d = state[3];
+    e = state[4];
+    /* 4 rounds of 20 operations each. Loop unrolled. */
+    R0(a, b, c, d, e, 0);
+    R0(e, a, b, c, d, 1);
+    R0(d, e, a, b, c, 2);
+    R0(c, d, e, a, b, 3);
+    R0(b, c, d, e, a, 4);
+    R0(a, b, c, d, e, 5);
+    R0(e, a, b, c, d, 6);
+    R0(d, e, a, b, c, 7);
+    R0(c, d, e, a, b, 8);
+    R0(b, c, d, e, a, 9);
+    R0(a, b, c, d, e, 10);
+    R0(e, a, b, c, d, 11);
+    R0(d, e, a, b, c, 12);
+    R0(c, d, e, a, b, 13);
+    R0(b, c, d, e, a, 14);
+    R0(a, b, c, d, e, 15);
+    R1(e, a, b, c, d, 16);
+    R1(d, e, a, b, c, 17);
+    R1(c, d, e, a, b, 18);
+    R1(b, c, d, e, a, 19);
+    R2(a, b, c, d, e, 20);
+    R2(e, a, b, c, d, 21);
+    R2(d, e, a, b, c, 22);
+    R2(c, d, e, a, b, 23);
+    R2(b, c, d, e, a, 24);
+    R2(a, b, c, d, e, 25);
+    R2(e, a, b, c, d, 26);
+    R2(d, e, a, b, c, 27);
+    R2(c, d, e, a, b, 28);
+    R2(b, c, d, e, a, 29);
+    R2(a, b, c, d, e, 30);
+    R2(e, a, b, c, d, 31);
+    R2(d, e, a, b, c, 32);
+    R2(c, d, e, a, b, 33);
+    R2(b, c, d, e, a, 34);
+    R2(a, b, c, d, e, 35);
+    R2(e, a, b, c, d, 36);
+    R2(d, e, a, b, c, 37);
+    R2(c, d, e, a, b, 38);
+    R2(b, c, d, e, a, 39);
+    R3(a, b, c, d, e, 40);
+    R3(e, a, b, c, d, 41);
+    R3(d, e, a, b, c, 42);
+    R3(c, d, e, a, b, 43);
+    R3(b, c, d, e, a, 44);
+    R3(a, b, c, d, e, 45);
+    R3(e, a, b, c, d, 46);
+    R3(d, e, a, b, c, 47);
+    R3(c, d, e, a, b, 48);
+    R3(b, c, d, e, a, 49);
+    R3(a, b, c, d, e, 50);
+    R3(e, a, b, c, d, 51);
+    R3(d, e, a, b, c, 52);
+    R3(c, d, e, a, b, 53);
+    R3(b, c, d, e, a, 54);
+    R3(a, b, c, d, e, 55);
+    R3(e, a, b, c, d, 56);
+    R3(d, e, a, b, c, 57);
+    R3(c, d, e, a, b, 58);
+    R3(b, c, d, e, a, 59);
+    R4(a, b, c, d, e, 60);
+    R4(e, a, b, c, d, 61);
+    R4(d, e, a, b, c, 62);
+    R4(c, d, e, a, b, 63);
+    R4(b, c, d, e, a, 64);
+    R4(a, b, c, d, e, 65);
+    R4(e, a, b, c, d, 66);
+    R4(d, e, a, b, c, 67);
+    R4(c, d, e, a, b, 68);
+    R4(b, c, d, e, a, 69);
+    R4(a, b, c, d, e, 70);
+    R4(e, a, b, c, d, 71);
+    R4(d, e, a, b, c, 72);
+    R4(c, d, e, a, b, 73);
+    R4(b, c, d, e, a, 74);
+    R4(a, b, c, d, e, 75);
+    R4(e, a, b, c, d, 76);
+    R4(d, e, a, b, c, 77);
+    R4(c, d, e, a, b, 78);
+    R4(b, c, d, e, a, 79);
+    /* Add the working vars back into context.state[] */
+    state[0] += a;
+    state[1] += b;
+    state[2] += c;
+    state[3] += d;
+    state[4] += e;
+    /* Wipe variables */
+    a = b = c = d = e = 0;
+#ifdef SHA1HANDSOFF
+    memset(block, '\0', sizeof(block));
+#endif
+}
+
+
+/* SHA1Init - Initialize new context */
+
+void SHA1Init(
+    SHA1_CTX * context
+)
+{
+    /* SHA1 initialization constants */
+    context->state[0] = 0x67452301;
+    context->state[1] = 0xEFCDAB89;
+    context->state[2] = 0x98BADCFE;
+    context->state[3] = 0x10325476;
+    context->state[4] = 0xC3D2E1F0;
+    context->count[0] = context->count[1] = 0;
+}
+
+
+/* Run your data through this. */
+
+void SHA1Update(
+    SHA1_CTX * context,
+    const unsigned char *data,
+    uint32_t len
+)
+{
+    uint32_t i;
+
+    uint32_t j;
+
+    j = context->count[0];
+    if ((context->count[0] += len << 3) < j)
+        context->count[1]++;
+    context->count[1] += (len >> 29);
+    j = (j >> 3) & 63;
+    if ((j + len) > 63)
+    {
+        memcpy(&context->buffer[j], data, (i = 64 - j));
+        SHA1Transform(context->state, context->buffer);
+        for (; i + 63 < len; i += 64)
+        {
+            SHA1Transform(context->state, &data[i]);
+        }
+        j = 0;
+    }
+    else
+        i = 0;
+    memcpy(&context->buffer[j], &data[i], len - i);
+}
+
+
+/* Add padding and return the message digest. */
+
+void SHA1Final(
+    unsigned char digest[20],
+    SHA1_CTX * context
+)
+{
+    unsigned i;
+
+    unsigned char finalcount[8];
+
+    unsigned char c;
+
+#if 0    /* untested "improvement" by DHR */
+    /* Convert context->count to a sequence of bytes
+     * in finalcount.  Second element first, but
+     * big-endian order within element.
+     * But we do it all backwards.
+     */
+    unsigned char *fcp = &finalcount[8];
+
+    for (i = 0; i < 2; i++)
+    {
+        uint32_t t = context->count[i];
+
+        int j;
+
+        for (j = 0; j < 4; t >>= 8, j++)
+            *--fcp = (unsigned char) t}
+#else
+    for (i = 0; i < 8; i++)
+    {
+        finalcount[i] = (unsigned char) ((context->count[(i >= 4 ? 0 : 1)] >> ((3 - (i & 3)) * 8)) & 255);      /* Endian independent */
+    }
+#endif
+    c = 0200;
+    SHA1Update(context, &c, 1);
+    while ((context->count[0] & 504) != 448)
+    {
+        c = 0000;
+        SHA1Update(context, &c, 1);
+    }
+    SHA1Update(context, finalcount, 8); /* Should cause a SHA1Transform() */
+    for (i = 0; i < 20; i++)
+    {
+        digest[i] = (unsigned char)
+            ((context->state[i >> 2] >> ((3 - (i & 3)) * 8)) & 255);
+    }
+    /* Wipe variables */
+    memset(context, '\0', sizeof(*context));
+    memset(&finalcount, '\0', sizeof(finalcount));
+}
+
+void SHA1(
+    char *hash_out,
+    const char *str,
+    uint32_t len)
+{
+    SHA1_CTX ctx;
+    unsigned int ii;
+
+    SHA1Init(&ctx);
+    for (ii=0; ii<len; ii+=1)
+        SHA1Update(&ctx, (const unsigned char*)str + ii, 1);
+    SHA1Final((unsigned char *)hash_out, &ctx);
+}
+

package/src/llama.cpp/examples/gguf-hash/deps/sha1/sha1.h

@@ -0,0 +1,52 @@
+#ifndef SHA1_H
+#define SHA1_H
+
+/*
+   SHA-1 in C
+   By Steve Reid <steve@edmweb.com>
+   100% Public Domain
+ */
+
+#include "stdint.h"
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
+typedef struct
+{
+    uint32_t state[5];
+    uint32_t count[2];
+    unsigned char buffer[64];
+} SHA1_CTX;
+
+void SHA1Transform(
+    uint32_t state[5],
+    const unsigned char buffer[64]
+    );
+
+void SHA1Init(
+    SHA1_CTX * context
+    );
+
+void SHA1Update(
+    SHA1_CTX * context,
+    const unsigned char *data,
+    uint32_t len
+    );
+
+void SHA1Final(
+    unsigned char digest[20],
+    SHA1_CTX * context
+    );
+
+void SHA1(
+    char *hash_out,
+    const char *str,
+    uint32_t len);
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif /* SHA1_H */