b10081
ggml-org/llama.cppb10081Jul 22, 2026by github-actions[bot]
AI Summary
Fixes a bug where draft repositories were not resolving to their requested sidecar models when using the --spec-type draft-dflash flag, ensuring speculative decoding works as expected.
Key Highlights
- Fixes draft repo sidecar resolution
- Enables proper speculative decoding with sidecar repos
- Wires sidecar discovery into the fallback pattern
New Features
- Speculative decoding sidecar support
Full Release Notes
<details open> common: resolve draft repo to its requested sidecar (#25955) With -hfd pointing to a repo shipping speculative sidecars, the draft resolved to the main model of that repo, since find_best_model() excludes sidecar files, and the explicit draft plan suppressed the sidecar discovery on the -hf repo. The draft plan already discovers its sidecars, they were just never consumed. Wire them as the draft, following the fallback pattern of the main plan, so this now works as expected: llama-server -hf repo -hfd repo --spec-type draft-dflash </details> **Website:** - <https://llama.app> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b10081/llama-b10081-bin-macos-arm64.tar.gz) - macOS Apple Silicon (arm64, KleidiAI enabled) [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23780) - [macOS Intel (x64)](https://github.com/ggml-org/llama.cpp/releases/download/b10081/llama-b10081-bin-macos-x64.tar.gz) - [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b10081/llama-b10081-xcframework.zip) **Linux:** - [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10081/llama-b10081-bin-ubuntu-x64.tar.gz) - [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10081/llama-b10081-bin-ubuntu-arm64.tar.gz) - [Ubuntu s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10081/llama-b10081-bin-ubuntu-s390x.tar.gz) - [Ubuntu x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b10081/llama-b10081-bin-ubuntu-vulkan-x64.tar.gz) - [Ubuntu arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b10081/llama-b10081-bin-ubuntu-vulkan-arm64.tar.gz) - [Ubuntu x64 (ROCm 7.2)](https://github.com/ggml-org/llama.cpp/releases/download/b10081/llama-b10081-bin-ubuntu-rocm-7.2-x64.tar.gz) - [Ubuntu x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b10081/llama-b10081-bin-ubuntu-openvino-2026.2.1-x64.tar.gz) - [Ubuntu x64 (SYCL FP32)](https://github.com/ggml-org/llama.cpp/releases/download/b10081/llama-b10081-bin-ubuntu-sycl-fp32-x64.tar.gz) - [Ubuntu x64 (SYCL FP16)](https://github.com/ggml-org/llama.cpp/releases/download/b10081/llama-b10081-bin-ubuntu-sycl-fp16-x64.tar.gz) **Android:** - [Android arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10081/llama-b10081-bin-android-arm64.tar.gz) **Windows:** - [Windows x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10081/llama-b10081-bin-win-cpu-x64.zip) - [Windows arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10081/llama-b10081-bin-win-cpu-arm64.zip) - [Windows arm64 (OpenCL Adreno)](https://github.com/ggml-org/llama.cpp/releases/download/b10081/llama-b10081-bin-win-opencl-adreno-arm64.zip) - [Windows x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/b10081/llama-b10081-bin-win-cuda-12.4-x64.zip) - [CUDA 12.4 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b10081/cudart-llama-bin-win-cuda-12.4-x64.zip) - [Windows x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b10081/llama-b10081-bin-win-cuda-13.3-x64.zip) - [CUDA 13.3 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b10081/cudart-llama-bin-win-cuda-13.3-x64.zip) - [Windows x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b10081/llama-b10081-bin-win-vulkan-x64.zip) - [Windows x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b10081/llama-b10081-bin-win-openvino-2026.2.1-x64.zip) - [Windows x64 (SYCL)](https://github.com/ggml-org/llama.cpp/releases/download/b10081/llama-b10081-bin-win-sycl-x64.zip) - [Windows x64 (HIP)](https://github.com/ggml-org/llama.cpp/releases/download/b10081/llama-b10081-bin-win-hip-radeon-x64.zip) **openEuler:** - [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23705) - openEuler x86 (310p) - openEuler x86 (910b, ACL Graph) - openEuler aarch64 (310p) - openEuler aarch64 (910b, ACL Graph) **UI:** - [UI](https://github.com/ggml-org/llama.cpp/releases/download/b10081/llama-b10081-ui.tar.gz)