spec : add ngram-mod

common/CMakeLists.txt

@@ -75,6 +75,8 @@ add_library(${TARGET} STATIC
     ngram-cache.h
     ngram-map.cpp
     ngram-map.h
+    ngram-mod.cpp
+    ngram-mod.h
     peg-parser.cpp
     peg-parser.h
     preset.cpp

common/arg.cpp

@@ -3396,7 +3396,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
         }
     ).set_examples({LLAMA_EXAMPLE_SPECULATIVE, LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_CLI}));
     add_opt(common_arg(
-        {"--spec-type"}, "[none|ngram-cache|ngram-simple|ngram-map-k|ngram-map-k4v]",
+        {"--spec-type"}, "[none|ngram-cache|ngram-simple|ngram-map-k|ngram-map-k4v|ngram-mod]",
         string_format("type of speculative decoding to use when no draft model is provided (default: %s)\n",
             common_speculative_type_to_str(params.speculative.type).c_str()),
         [](common_params & params, const std::string & value) {
@@ -3410,6 +3410,8 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
                 params.speculative.type = COMMON_SPECULATIVE_TYPE_NGRAM_MAP_K;
             } else if (value == "ngram-map-k4v") {
                 params.speculative.type = COMMON_SPECULATIVE_TYPE_NGRAM_MAP_K4V;
+            } else if (value == "ngram-mod") {
+                params.speculative.type = COMMON_SPECULATIVE_TYPE_NGRAM_MOD;
             } else {
                 throw std::invalid_argument("unknown speculative decoding type without draft model");
             }

common/common.h

@@ -171,6 +171,7 @@ enum common_speculative_type {
     COMMON_SPECULATIVE_TYPE_NGRAM_SIMPLE,  // simple self-speculative decoding
     COMMON_SPECULATIVE_TYPE_NGRAM_MAP_K,   // self-speculative decoding with n-gram keys only
     COMMON_SPECULATIVE_TYPE_NGRAM_MAP_K4V, // self-speculative decoding with n-gram keys and 4 m-gram values
+    COMMON_SPECULATIVE_TYPE_NGRAM_MOD,
     COMMON_SPECULATIVE_TYPE_NGRAM_CACHE,   // self-speculative decoding with 3-level n-gram cache
     COMMON_SPECULATIVE_TYPE_COUNT          // number of types, unknown type
 };
@@ -252,6 +253,8 @@ struct common_params_model {
     std::string name        = ""; // in format <user>/<model>[:<tag>] (tag is optional)     // NOLINT
 };
 
+struct common_ngram_mod;
+
 struct common_params_speculative {
     common_speculative_type type = COMMON_SPECULATIVE_TYPE_NONE; // type of speculative decoding
 
@@ -269,6 +272,8 @@ struct common_params_speculative {
     uint16_t ngram_check_rate =  1; // check rate for ngram lookup
     uint16_t ngram_min_hits   =  1; // minimum hits at ngram/mgram lookup for mgram to be proposed
 
+    std::shared_ptr<common_ngram_mod> ngram_mod;
+
     std::string lookup_cache_static;  // path of static ngram cache file for lookup decoding           // NOLINT
     std::string lookup_cache_dynamic; // path of dynamic ngram cache file for lookup decoding          // NOLINT
 

common/ngram-map.cpp

@@ -7,6 +7,21 @@
 #include <cstdio>
 #include <sstream>
 
+// Print the values of a sublist of `llama_tokens & inp` to a string in the form [v0, v1, v2, ...].
+static std::string common_tokens_to_str(const llama_tokens & inp, size_t start, size_t length) {
+    std::ostringstream oss;
+    oss << '[';
+    for (size_t i = 0; i < length; ++i) {
+        if (i > 0) {
+            oss << ", ";
+        }
+        oss << inp[start + i];
+    }
+    oss << ']';
+    return oss.str();
+}
+
+
 // n-gram simple
 //
 
@@ -100,8 +115,6 @@ llama_tokens common_ngram_simple_draft(
 // maximum number of counted values of a ngram map value.
 #define COMMON_NGRAM_MAX_VALUE_COUNT 16380
 
-static std::string common_tokens_to_str(const llama_tokens & inp, size_t start, size_t length);
-
 void common_ngram_map_draft(common_ngram_map & map,
         const llama_tokens & inp, llama_token sampled,
         llama_tokens & draft) {
@@ -347,21 +360,3 @@ void common_ngram_map_accept(common_ngram_map & map, uint16_t n_accepted) {
             n_accepted, curr_value.n_accepted);
     curr_value.n_accepted = n_accepted;
 }
-
-// Helper functions.
-//
-
-// Print the values of a sublist of `llama_tokens & inp` to a string in the form [v0, v1, v2, ...].
-std::string common_tokens_to_str(const llama_tokens & inp, size_t start, size_t length) {
-    std::ostringstream oss;
-    oss << '[';
-    for (size_t i = 0; i < length; ++i) {
-        if (i > 0) {
-            oss << ", ";
-        }
-        oss << inp[start + i];
-    }
-    oss << ']';
-    return oss.str();
-}
-

common/ngram-map.h

@@ -11,6 +11,7 @@
 //
 
 #include "llama.h"
+#include "common.h"
 
 #include <vector>
 

common/ngram-mod.cpp

@@ -0,0 +1,60 @@
+#include "ngram-mod.h"
+
+//
+// common_ngram_mod
+//
+
+common_ngram_mod::common_ngram_mod(uint16_t n, size_t size) : n(n), used(0) {
+    entries.resize(size);
+
+    reset();
+}
+
+size_t common_ngram_mod::idx(const entry_t * tokens) const {
+    size_t res = 0;
+
+    for (size_t i = 0; i < n; ++i) {
+        res = res*6364136223846793005ULL + tokens[i];
+    }
+
+    res = res % entries.size();
+
+    return res;
+}
+
+void common_ngram_mod::add(const entry_t * tokens) {
+    const size_t i = idx(tokens);
+
+    if (entries[i] == EMPTY) {
+        used++;
+    }
+
+    entries[i] = tokens[n];
+}
+
+common_ngram_mod::entry_t common_ngram_mod::get(const entry_t * tokens) const {
+    const size_t i = idx(tokens);
+
+    return entries[i];
+}
+
+void common_ngram_mod::reset() {
+    std::fill(entries.begin(), entries.end(), EMPTY);
+    used = 0;
+}
+
+size_t common_ngram_mod::get_n() const {
+    return n;
+}
+
+size_t common_ngram_mod::get_used() const {
+    return used;
+}
+
+size_t common_ngram_mod::size() const {
+    return entries.size();
+}
+
+size_t common_ngram_mod::size_bytes() const {
+    return entries.size() * sizeof(entries[0]);
+}

common/ngram-mod.h

@@ -0,0 +1,37 @@
+#pragma once
+
+#include <cstdint>
+#include <vector>
+
+//
+// common_ngram_mod
+// ref: https://github.com/ggml-org/llama.cpp/pull/19164
+//
+
+// basic n-gram hasher
+struct common_ngram_mod {
+    using entry_t = int32_t;
+
+    static constexpr entry_t EMPTY = -1;
+
+    common_ngram_mod(uint16_t n, size_t size);
+
+    size_t  idx(const entry_t * tokens) const;
+    void    add(const entry_t * tokens);
+    entry_t get(const entry_t * tokens) const; // return -1 if not found
+
+    void reset();
+
+    size_t get_n()    const;
+    size_t get_used() const;
+
+    size_t size()       const;
+    size_t size_bytes() const;
+
+private:
+    size_t n; // ngram size to hash
+
+    size_t used;
+
+    std::vector<entry_t> entries;
+};