b10413

ggml-org/llama.cppb10413Aug 13, 2026by github-actions[bot]
AI Summary

Adds automatic detection of speculative decoding types (dspark and dflash) when loading local draft models from GGUF metadata.
Key Highlights

Auto-detect spec type from draft GGUF metadata (#26814)
Add logging to inform users when auto-detection fires
New Features

Auto-detection of speculative decoding types for local draft models
Full Release Notes

<details open>

common : auto-detect spec type from draft GGUF metadata (#26814)

* common : auto-detect spec type from draft GGUF metadata

When -md loads a local draft model without --spec-type, the sidecar
inference in common_models_handler_apply only checks HF repo sidecars
and misses local files. The draft model loads into VRAM but speculative
decoding never activates (types stays NONE).

Read general.architecture from the draft GGUF header and map:
  dflash + markov_w1.weight tensor -> draft-dspark
  dflash without markov head        -> draft-dflash

Assisted-by: opencode

* common : address review feedback on spec-type auto-detect PR

- Fix comment spacing to match surrounding style (/* .x = */ not /*.x =*/)
- Add LOG_INF when auto-detection fires so users can see why spec decoding enabled
- Document single-file assumption for split-GGUF edge case

Addresses bot review feedback on #26814.

* common : move spec-type GGUF auto-detect into speculative module

- add common_speculative_types_from_gguf() in speculative.cpp/.h
- use gguf_context_ptr (RAII) from ggml-cpp.h
- reduce comments to a single line per AGENTS.md style

Addresses review feedback on #26814

* common : add doc note and join SPC_INF line in spec-type auto-detect

Assisted-by: opencode

</details>

**Website:**
- <https://llama.app>

**macOS/iOS:**
- [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b10413/llama-b10413-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/b10413/llama-b10413-bin-macos-x64.tar.gz)
- [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b10413/llama-b10413-xcframework.zip)

**Linux:**
- [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10413/llama-b10413-bin-ubuntu-x64.tar.gz)
- [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10413/llama-b10413-bin-ubuntu-arm64.tar.gz)
- [Ubuntu s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10413/llama-b10413-bin-ubuntu-s390x.tar.gz)
- [Ubuntu x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b10413/llama-b10413-bin-ubuntu-vulkan-x64.tar.gz)
- [Ubuntu arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b10413/llama-b10413-bin-ubuntu-vulkan-arm64.tar.gz)
- Ubuntu x64 (ROCm 7.14)[DISABLED](https://github.com/ggml-org/llama.cpp/pull/26969)
- [Ubuntu x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b10413/llama-b10413-bin-ubuntu-openvino-2026.2.1-x64.tar.gz)
- [Ubuntu x64 (SYCL FP32)](https://github.com/ggml-org/llama.cpp/releases/download/b10413/llama-b10413-bin-ubuntu-sycl-fp32-x64.tar.gz)
- [Ubuntu x64 (SYCL FP16)](https://github.com/ggml-org/llama.cpp/releases/download/b10413/llama-b10413-bin-ubuntu-sycl-fp16-x64.tar.gz)

**Android:**
- [Android arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10413/llama-b10413-bin-android-arm64.tar.gz)

**Windows:**
- [Windows x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10413/llama-b10413-bin-win-cpu-x64.zip)
- [Windows arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10413/llama-b10413-bin-win-cpu-arm64.zip)
- [Windows arm64 (OpenCL Adreno)](https://github.com/ggml-org/llama.cpp/releases/download/b10413/llama-b10413-bin-win-opencl-adreno-arm64.zip)
- [Windows x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/b10413/llama-b10413-bin-win-cuda-12.4-x64.zip) - [CUDA 12.4 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b10413/cudart-llama-bin-win-cuda-12.4-x64.zip)
- [Windows x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b10413/llama-b10413-bin-win-cuda-13.3-x64.zip) - [CUDA 13.3 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b10413/cudart-llama-bin-win-cuda-13.3-x64.zip)
- [Windows arm64 (CUDA 13) (preview)](https://github.com/ggml-org/llama.cpp/releases/download/b10413/llama-b10413-bin-win-cuda-13.4-arm64.zip) - [CUDA 13.4 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b10413/cudart-llama-bin-win-cuda-13.4-arm64.zip)
- [Windows x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b10413/llama-b10413-bin-win-vulkan-x64.zip)
- [Windows x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b10413/llama-b10413-bin-win-openvino-2026.2.1-x64.zip)
- [Windows x64 (SYCL)](https://github.com/ggml-org/llama.cpp/releases/download/b10413/llama-b10413-bin-win-sycl-x64.zip)
- [Windows x64 (ROCm 7.14)](https://github.com/ggml-org/llama.cpp/releases/download/b10413/llama-b10413-bin-win-rocm-7.14-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/b10413/llama-b10413-ui.tar.gz)