unicode,test: add Qwen3.5 non-backtracking tokenizer handler and regr… (#22110)

Kabir08 · Kabir · aldehir · web-flow · commit 42532afff439 · 2026-05-14T11:03:40.000+02:00
* unicode,test: add Qwen3.5 non-backtracking tokenizer handler and regression tests - Add unicode_regex_split_custom_qwen35() to [src/unicode.cpp](src/unicode.cpp), a non-backtracking handler for Qwen3.5's [\p{L}\p{M}]+ regex (letters + combining marks). - Register the handler in the custom tokenizer dispatch table to prevent stack overflows on long inputs (fixes #21919). - Add [models/ggml-vocab-qwen35.gguf](models/ggml-vocab-qwen35.gguf) (test vocab), [models/ggml-vocab-qwen35.gguf.inp](models/ggml-vocab-qwen35.gguf.inp) (test cases), and [models/ggml-vocab-qwen35.gguf.out](models/ggml-vocab-qwen35.gguf.out) (expected output) for regression testing. - Update [tests/CMakeLists.txt](tests/CMakeLists.txt) to include the new test entry. This mirrors the Qwen2 fix (commit 0d049d6), but adapts for Qwen3.5's regex. Ensures robust Unicode tokenization and prevents std::regex stack overflows. Closes #21919. * fix: enhance regex handling for Qwen3.5 tokenizer to include accent marks * cont : remove trailing whitespace --------- Co-authored-by: Kabir <kabir@example.com> Co-authored-by: Alde Rojas <hello@alde.dev>
diff --git a/models/ggml-vocab-qwen35.gguf b/models/ggml-vocab-qwen35.gguf
diff --git a/models/ggml-vocab-qwen35.gguf.inp b/models/ggml-vocab-qwen35.gguf.inp
@@ -0,0 +1,120 @@
+ied 4 ½ months
+__ggml_vocab_test__
+Äpfel
+__ggml_vocab_test__
+
+__ggml_vocab_test__
+ 
+__ggml_vocab_test__
+  
+__ggml_vocab_test__
+   
+__ggml_vocab_test__
+	
+__ggml_vocab_test__
+
+
+__ggml_vocab_test__
+
+
+
+__ggml_vocab_test__
+
+
+
+
+__ggml_vocab_test__
+	
+
+__ggml_vocab_test__
+Hello world
+__ggml_vocab_test__
+ Hello world
+__ggml_vocab_test__
+Hello World
+__ggml_vocab_test__
+ Hello World
+__ggml_vocab_test__
+ Hello World!
+__ggml_vocab_test__
+Hello, world!
+__ggml_vocab_test__
+ Hello, world!
+__ggml_vocab_test__
+ this is 🦙.cpp
+__ggml_vocab_test__
+w048 7tuijk dsdfhu
+__ggml_vocab_test__
+нещо на Български
+__ggml_vocab_test__
+កាន់តែពិសេសអាចខលចេញ
+__ggml_vocab_test__
+🚀 (normal) 😶‍🌫️ (multiple emojis concatenated) ✅ (only emoji that has its own token)
+__ggml_vocab_test__
+Hello
+__ggml_vocab_test__
+ Hello
+__ggml_vocab_test__
+  Hello
+__ggml_vocab_test__
+   Hello
+__ggml_vocab_test__
+    Hello
+__ggml_vocab_test__
+    Hello
+    Hello
+__ggml_vocab_test__
+ (
+__ggml_vocab_test__
+
+ =
+__ggml_vocab_test__
+' era
+__ggml_vocab_test__
+Hello, y'all! How are you 😁 ?我想在apple工作1314151天～
+__ggml_vocab_test__
+!!!!!!
+__ggml_vocab_test__
+3
+__ggml_vocab_test__
+33
+__ggml_vocab_test__
+333
+__ggml_vocab_test__
+3333
+__ggml_vocab_test__
+33333
+__ggml_vocab_test__
+333333
+__ggml_vocab_test__
+3333333
+__ggml_vocab_test__
+33333333
+__ggml_vocab_test__
+333333333
+__ggml_vocab_test__
+Cửa Việt
+__ggml_vocab_test__
+ discards
+__ggml_vocab_test__
+
+ 
+
+ 
+
+
+ 	 		 	
+  
+   
+    
+     
+🚀 (normal) 😶‍🌫️ (multiple emojis concatenated) ✅ 🦙🦙 3 33 333 3333 33333 333333 3333333 33333333 3.3 3..3 3...3 កាន់តែពិសេសអាច😁 ?我想在apple工作1314151天～ ------======= нещо на Български ''''''```````""""......!!!!!!?????? I've been 'told he's there, 'RE you sure? 'M not sure I'll make it, 'D you like some tea? We'Ve a'lL
+__ggml_vocab_test__
+é
+__ggml_vocab_test__
+résumé
+__ggml_vocab_test__
+àààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààààà
+__ggml_vocab_test__
+Vieết Nam
+__ggml_vocab_test__
diff --git a/models/ggml-vocab-qwen35.gguf.out b/models/ggml-vocab-qwen35.gguf.out
@@ -0,0 +1,50 @@
+1122 220 19 220 26062 3951
+86975 15897 301
+
+220
+256
+262
+197
+198
+271
+1406
+1572
+9707 1879
+21927 1879
+9707 4337
+21927 4337
+21927 4337 0
+9707 11 1879 0
+21927 11 1879 0
+419 374 11162 99 247 13 10821
+86 15 19 23 220 22 83 1963 41808 11472 2940 16739
+78762 14144 1456 13073 63471 33594 3038 133178 79012
+146394 97529 241 44258 233 146568 44258 224 147603 20879 115 146280 44258 223 146280 147272 97529 227 147805 148301 147270 44258 223 146848
+145836 320 8252 8 26525 114 378 235 149921 30543 320 35673 99066 97534 8 25521 227 320 3243 42365 429 702 1181 1828 3950 8
+9707
+21927
+220 21927
+256 21927
+262 21927
+262 21927 198 262 21927
+320
+198 284
+6 11385
+9707 11 379 64848 0 2585 525 498 26525 223 937 104100 18493 22377 99257 16 18 16 19 16 20 16 35727 21216
+17085 2928
+18
+18 18
+18 18 18
+18 18 18 18
+18 18 18 18 18
+18 18 18 18 18 18
+18 18 18 18 18 18 18
+18 18 18 18 18 18 18 18
+18 18 18 18 18 18 18 18 18
+34 90063 128324
+2560 2347
+198 4710 14731 65497 7847 1572 2303 78672 10947 145836 320 8252 8 26525 114 378 235 149921 30543 320 35673 99066 97534 8 25521 227 11162 99 247 149955 220 18 220 18 18 220 18 18 18 220 18 18 18 18 220 18 18 18 18 18 220 18 18 18 18 18 18 220 18 18 18 18 18 18 18 220 18 18 18 18 18 18 18 18 220 18 13 18 220 18 496 18 220 18 1112 18 220 146394 97529 241 44258 233 146568 44258 224 147603 20879 115 146280 44258 223 146280 147272 97529 227 144534 937 104100 18493 22377 99257 16 18 16 19 16 20 16 35727 21216 55460 53237 18658 14144 1456 13073 63471 33594 3038 133178 79012 3355 4605 4605 13874 13874 73594 3014 3014 28149 17085 2928 26610 7646 358 3003 1012 364 83 813 566 594 1052 11 364 787 498 2704 30 364 44 537 2704 358 3278 1281 432 11 364 35 498 1075 1045 15243 30 1205 6 42612 264 63866 43
+68 53839
+265 53839 31323 53839
+64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549 64 96549
+53 645 51580 29974
diff --git a/src/unicode.cpp b/src/unicode.cpp
@@ -605,6 +605,136 @@ static std::vector<size_t> unicode_regex_split_custom_qwen2(const std::string &
     return bpe_offsets;
 }
 
+// Qwen3.5 system regex: "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+"
+// Compared to Qwen2, letter-runs also consume Unicode combining marks (\p{M}): [\p{L}\p{M}]+ instead of \p{L}+
+static std::vector<size_t> unicode_regex_split_custom_qwen35(const std::string & text, const std::vector<size_t> & offsets) {
+    std::vector<size_t> bpe_offsets; // store the offset of each word
+    bpe_offsets.reserve(offsets.size()); // Reserve memory for the approximate size
+
+    const auto cpts = unicode_cpts_from_utf8(text);
+
+    size_t start = 0;
+    for (auto offset : offsets) {
+        const size_t offset_ini = start;
+        const size_t offset_end = start + offset;
+        assert(offset_end <= cpts.size());
+        start = offset_end;
+
+        static const uint32_t OUT_OF_RANGE = 0xFFFFFFFF;
+        auto _get_cpt = [&] (const size_t pos) -> uint32_t {
+            return (offset_ini <= pos && pos < offset_end) ? cpts[pos] : OUT_OF_RANGE;
+        };
+
+        auto _get_flags = [&] (const size_t pos) -> unicode_cpt_flags {
+            return (offset_ini <= pos && pos < offset_end) ? unicode_cpt_flags_from_cpt(cpts[pos]) : unicode_cpt_flags{};
+        };
+
+        size_t _prev_end = offset_ini;
+        auto _add_token = [&] (const size_t end) -> size_t {
+            assert(_prev_end <= end && end <= offset_end);
+            size_t len = end - _prev_end;
+            if (len > 0) {
+                bpe_offsets.push_back(len);
+            }
+            _prev_end = end;
+            return len;
+        };
+
+        for (size_t pos = offset_ini; pos < offset_end; /*pos++*/ ) {
+            const uint32_t cpt = _get_cpt(pos);
+            const auto flags = _get_flags(pos);
+
+            // regex: (?i:'s|'t|'re|'ve|'m|'ll|'d) // case insensitive
+            if (cpt == '\'' && pos+1 < offset_end) {
+                uint32_t cpt_next = unicode_tolower(_get_cpt(pos+1));
+                if (cpt_next == 's' || cpt_next == 't' || cpt_next == 'm' || cpt_next == 'd') {
+                    pos += _add_token(pos+2);
+                    continue;
+                }
+                if (pos+2 < offset_end) {
+                    uint32_t cpt_next_next = unicode_tolower(_get_cpt(pos+2));
+                    if ((cpt_next == 'r' && cpt_next_next == 'e') ||
+                        (cpt_next == 'v' && cpt_next_next == 'e') ||
+                        (cpt_next == 'l' && cpt_next_next == 'l')) {
+                        pos += _add_token(pos+3);
+                        continue;
+                    }
+                }
+            }
+
+            // regex: [^\r\n\p{L}\p{N}]?[\p{L}\p{M}]+
+            if (!(cpt == '\r' || cpt == '\n' || flags.is_number)) {
+                if (flags.is_letter || flags.is_accent_mark || _get_flags(pos + 1).is_accent_mark || _get_flags(pos+1).is_letter) {
+                    pos++;
+                    while (_get_flags(pos).is_letter || _get_flags(pos).is_accent_mark) {
+                        pos++;
+                    }
+                    _add_token(pos);
+                    continue;
+                }
+            }
+
+            // regex: \p{N}
+            if (flags.is_number) {
+                pos++;
+                _add_token(pos);
+                continue;
+            }
+
+            // regex: <space>?[^\s\p{L}\p{M}\p{N}]+[\r\n]*
+            auto flags2 = (cpt == ' ' ? _get_flags(pos+1) : flags);
+            if (!(flags2.is_whitespace | flags2.is_letter | flags2.is_accent_mark | flags2.is_number) && flags.as_uint()) {
+                pos += (cpt == ' ');
+                while (!(flags2.is_whitespace | flags2.is_letter | flags2.is_accent_mark | flags2.is_number) && flags2.as_uint()) {
+                    flags2 = _get_flags(++pos);
+                }
+                uint32_t cpt2 = _get_cpt(pos);
+                while (cpt2 == '\r' || cpt2 == '\n') {
+                    cpt2 = _get_cpt(++pos);
+                }
+                _add_token(pos);
+                continue;
+            }
+
+            size_t num_whitespaces = 0;
+            size_t last_end_r_or_n = 0;
+            while (_get_flags(pos+num_whitespaces).is_whitespace) {
+                uint32_t cpt2 = _get_cpt(pos+num_whitespaces);
+                if (cpt2 == '\r' || cpt2 == '\n') {
+                    last_end_r_or_n = pos + num_whitespaces + 1;
+                }
+                num_whitespaces++;
+            }
+
+            // regex: \s*[\r\n]+
+            if (last_end_r_or_n > 0) {
+                pos = last_end_r_or_n;
+                _add_token(pos);
+                continue;
+            }
+
+            // regex: \s+(?!\S)
+            if (num_whitespaces > 1 && _get_cpt(pos+num_whitespaces) != OUT_OF_RANGE) {
+                pos += num_whitespaces - 1;
+                _add_token(pos);
+                continue;
+            }
+
+            // regex: \s+
+            if (num_whitespaces > 0) {
+                pos += num_whitespaces;
+                _add_token(pos);
+                continue;
+            }
+
+            // no matches
+            _add_token(++pos);
+        }
+    }
+
+    return bpe_offsets;
+}
+
 template <typename CharT>
 static std::vector<size_t> unicode_regex_split_stl(const std::basic_string<CharT> & text, const std::basic_string<CharT> & regex, const std::vector<size_t> & offsets) {
     using BidirIt = typename std::basic_string<CharT>::const_iterator;
@@ -929,6 +1059,9 @@ static std::vector<size_t> unicode_regex_split_custom(const std::string & text,
     } else if (
            regex_expr == "(?:'[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+") {
         bpe_offsets = unicode_regex_split_custom_qwen2(text, offsets);
+    } else if (
+           regex_expr == "(?:'[sS]|'[tT]|'[rR][eE]|'[vV][eE]|'[mM]|'[lL][lL]|'[dD])|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+") {
+        bpe_offsets = unicode_regex_split_custom_qwen35(text, offsets);
     } else if (regex_expr == "\\p{Han}+") {
         // K2's first pattern - handle all K2 patterns together
         bpe_offsets = unicode_regex_split_custom_kimi_k2(text, offsets);
diff --git a/tests/CMakeLists.txt b/tests/CMakeLists.txt
@@ -131,6 +131,7 @@ llama_test(test-tokenizer-0 NAME test-tokenizer-0-llama-spm         ARGS ${PROJE
 llama_test(test-tokenizer-0 NAME test-tokenizer-0-mpt               ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-mpt.gguf)
 llama_test(test-tokenizer-0 NAME test-tokenizer-0-phi-3             ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-phi-3.gguf)
 llama_test(test-tokenizer-0 NAME test-tokenizer-0-qwen2             ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-qwen2.gguf)
+llama_test(test-tokenizer-0 NAME test-tokenizer-0-qwen35            ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-qwen35.gguf)
 llama_test(test-tokenizer-0 NAME test-tokenizer-0-refact            ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-refact.gguf)
 llama_test(test-tokenizer-0 NAME test-tokenizer-0-starcoder         ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-starcoder.gguf)
 
