# ggerganov/llama.cpp b9148: b9148 — retained record

> Retained github record from github:ggerganov/llama.cpp.

Canonical: https://highsignal.app/data/records/0490f5507d16f8ef

[← sources](https://highsignal.app/data)


source: [github](https://highsignal.app/data/github) (github:ggerganov/llama.cpp)  published 2026-05-14 15:11 ingested 2026-05-15 08:50

[original source ↗](https://github.com/ggml-org/llama.cpp/releases/tag/b9148)

## extract

<details open>

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

* unicode,test: add Qwen3.5 non-backtracking tokenizer handler and regression tests

- Add unicode_regex_split_custom_qwen35() to [src/unicode.cpp](https://highsignal.app/data/records/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](https://highsignal.app/data/records/models/ggml-vocab-qwen35.gguf) (test vocab), [models/ggml-vocab-qwen35.gguf.inp](https://highsignal.app/data/records/models/ggml-vocab-qwen35.gguf.inp) (test cases), and [models/ggml-vocab-qwen35.gguf.out](https://highsignal.app/data/records/models/ggml-vocab-qwen35.gguf.out) (expected output) for regression testing.
- Update [tests/CMakeLists.txt](https://highsignal.app/data/records/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>

</details>

**macOS/iOS:**
- [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b9148/llama-b9148-bin-macos-arm64.tar.gz)
- [macOS Apple Silicon (arm64, KleidiAI enabled)](https://github.com/ggml-org/llama.cpp/releases/download/b9148/llama-b9148-bin-macos-arm64-kleidiai.tar.gz)
- [macOS Intel (x64)](https://github.com/ggml-org/llama.cpp/releases/download/b9148/llama-b9148-bin-macos-x64.tar.gz)
- [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b9148/llama-b9148-xcframework.zip)

**Linux:**
- [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9148/llama-b9148-bin-ubuntu-x64.tar.gz)
- [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9148/llama-b9148-bin-ubuntu-arm64.tar.gz)
- [Ubuntu s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9148/llama-b9148-bin-ubuntu-s390x.tar.gz)
- [Ubuntu x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b9148/llama-b9148-bin-ubuntu-vulkan-x64.tar.gz)
- [Ubuntu arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b9148/llama-b9148-bin-ubuntu-vulkan-arm64.tar.gz)
- [Ubuntu x64 (ROCm 7.2)](https://github.com/ggml-org/llama.cpp/releases/download/b9148/llama-b9148-bin-ubuntu-rocm-7.2-x64.tar.gz)
- [Ubuntu x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b9148/llama-b9148-bin-ubuntu-openvino-2026.0-x64.tar.gz)
- [Ubuntu x64 (SYCL FP32)](https://github.com/ggml-org/llama.cpp/releases/download/b9148/llama-b9148-bin-ubuntu-sycl-fp32-x64.tar.gz)
- [Ubuntu x64 (SYCL FP16)](https://github.com/ggml-org/llama.cpp/releases/download/b9148/llama-b9148-bin-ubuntu-sycl-fp16-x64.tar.gz)

**Android:**
- [Android arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9148/llama-b9148-bin-android-arm64.tar.gz)

**Windows:**
- [Windows x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9148/llama-b9148-bin-win-cpu-x64.zip)
- [Windows arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9148/llama-b9148-bin-win-cpu-arm64.zip)
- [Windows x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/b9148/llama-b9148-bin-win-cuda-12.4-x64.zip) - [CUDA 12.4 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b9148/cudart-llama-bin-win-cuda-12.4-x64.zip)
- [Windows x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b9148/llama-b9148-bin-win-cuda-13.1-x64.zip) - [CUDA 13.1 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b9148/cudart-llama-bin-win-cuda-13.1-x64.zip)
- [Windows x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b9148/llama-b9148-bin-win-vulkan-x64.zip)
- [Windows x64 (SYCL)](https://github.com/ggml-org/llama.cpp/releases/download/b9148/llama-b9148-bin-win-sycl-x64.zip)
- [Windows x64 (HIP)](https://github.com/ggml-org/llama.cpp/releases/download/b9148/llama-b9148-bin-win-hip-radeon-x64.zip)

**openEuler:**
- [openEuler x86 (310p)](https://github.com/ggml-org/llama.cpp/releases/download/b9148/llama-b9148-bin-310p-openEuler-x86.tar.gz)
- [openEuler x86 (910b, ACL Graph)](https://github.com/ggml-org/llama.cpp/releases/download/b9148/llama-b9148-bin-910b-openEuler-x86-aclgraph.tar.gz)
- [openEuler aarch64 (310p)](https://github.com/ggml-org/llama.cpp/releases/download/b9148/llama-b9148-bin-310p-openEuler-aarch64.tar.gz)
- [openEuler aarch64 (910b, ACL Graph)](https://github.com/ggml-org/llama.cpp/releases/download/b9148/llama-b9148-bin-910b-openEuler-aarch64-aclgraph.tar.gz)

## retained text

No document body was retained for this record — only its metadata was stored.
