ggml-org/llama.cpp b12065: b12065

0.47
inference-engines · v1 · published 11/3/2026, 8:09:39 AM · TLP:CLEAR
ai.inference
Source evidence ↗
Entities

repository: ggml-org/llama.cpp
Assessment

Fact summary

low · heuristic
<details open> kv-cache : never return 0 kv_rows for sequences without cells (#31570) A cache that shares the cells of another one (f.ex. the gemma4 assistant) can build a graph before its sequences have any cells, f.ex. at the server warmup
Technical delta

low · heuristic
Automated delta unavailable (heuristic mode).
Defensive significance

low · heuristic
None identified (heuristic mode).
Extracted text

<details open>

kv-cache : never return 0 kv_rows for sequences without cells (#31570)

A cache that shares the cells of another one (f.ex. the gemma4 assistant) can build a graph before its sequences have any cells, f.ex. at the server warmup. get_n_kv_rows() then returned 0, which means that kv_rows are not used, so the graph fell back to the dense KQ mask and the scheduler re-planned for it. Later graphs with larger masks then aborted with GGML_SCHED_DEBUG_REALLOC=1.

</details>

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

**Attestations:**
- <https://github.com/ggml-org/llama.cpp/attestations/63009461>

**macOS/iOS:**
- [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b12065/llama-b12065-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/b12065/llama-b12065-bin-macos-x64.tar.gz)
- [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b12065/llama-b12065-xcframework.zip)

**Linux:**
- [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b12065/llama-b12065-bin-ubuntu-x64.tar.gz)
- [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b12065/llama-b12065-bin-ubuntu-arm64.tar.gz)
- [Ubuntu s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b12065/llama-b12065-bin-ubuntu-s390x.tar.gz)
- [Ubuntu 26.04 s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b12065/llama-b12065-bin-ubuntu-26.04-s390x.tar.gz)
- [Ubuntu 26.04 s390x (zDNN)](https://github.com/ggml-org/llama.cpp/releases/download/b12065/llama-b12065-bin-ubuntu-zdnn-s390x.tar.gz)
- [Ubuntu x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b12065/llama-b12065-bin-ubuntu-vulkan-x64.tar.gz)
- [Ubuntu arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b12065/llama-b12065-bin-ubuntu-vulkan-arm64.tar.gz)
- [Ubuntu x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/b12065/llama-b12065-bin-ubuntu-cuda-12.8-x64.tar.gz) - [CUDA 12.8 libraries](https://github.com/ggml-org/llama.cpp/releases/download/b12065/cudart-llama-b12065-bin-ubuntu-cuda-12.8-x64.tar.gz)
- [Ubuntu x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b12065/llama-b12065-bin-ubuntu-cuda-13.4-x64.tar.gz) - [CUDA 13.4 libraries](https://github.com/ggml-org/llama.cpp/releases/download/b12065/cudart-llama-b12065-bin-ubuntu-cuda-13.4-x64.tar.gz)
- [Ubuntu arm64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b12065/llama-b12065-bin-ubuntu-cuda-13.4-arm64.tar.gz) - [CUDA 13.4 libraries](https://github.com/ggml-org/llama.cpp/releases/download/b12065/cudart-llama-b12065-bin-ubuntu-cuda-13.4-arm64.tar.gz)
- [Ubuntu x64 (ROCm 10.0)](https://github.com/ggml-org/llama.cpp/releases/download/b12065/llama-b12065-bin-ubuntu-rocm-10.0-x64.tar.gz)
- [Ubuntu x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b12065/llama-b12065-bin-ubuntu-openvino-2026.4.1-x64.tar.gz)
- [Ubuntu x64 (SYCL FP32)](https://github.com/ggml-org/llama.cpp/releases/download/b12065/llama-b12065-bin-ubuntu-sycl-fp32-x64.tar.gz)
- [Ubuntu x64 (SYCL FP16)](https://github.com/ggml-org/llama.cpp/releases/download/b12065/llama-b12065-bin-ubuntu-sycl-fp16-x64.tar.gz)
- [Linux arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU)](https://github.com/ggml-org/llama.cpp/releases/download/b12065/llama-b12065-bin-linux-arm64-snapdragon.tar.gz) - [setup guide](https://github.com/ggml-org/llama.cpp/blob/master/docs/backend/snapdragon/linux.md)

**Android:**
- [Android arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b12065/llama-b12065-bin-android-arm64.tar.gz)
- [Android arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU)](https://github.com/ggml-org/llama.cpp/releases/download/b12065/llama-b12065-bin-android-arm64-snapdragon.tar.gz) - [setup guide](https://github.com/ggml-org/llama.cpp/blob/master/docs/backend/snapdragon/README.md)

**Windows:**
- [Windows x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b12065/llama-b12065-bin-win-cpu-x64.zip)
- [Windows arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b12065/llama-b12065-bin-win-cpu-arm64.zip)
- [Windows arm64 (OpenCL Adreno)](https://github.com/ggml-org/llama.cpp/releases/download/b12065/llama-b12065-bin-win-opencl-adreno-arm64.zip)
- [Windows x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/b12065/llama-b12065-bin-win-cuda-12.4-x64.zip) - [CUDA 12.4 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b12065/cudart-llama-bin-win-cuda-12.4-x64.zip)
- [Windows x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b12065/llama-b12065-bin-win-cuda-13.4-x64.zip) - [CUDA 13.4 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b12065/cudart-llama-bin-win-cuda-13.4-x64.zip)
- [Windows arm64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b12065/llama-b12065-bin-win-cuda-13.4-arm64.zip) - [CUDA 13.4 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b12065/cudart-llama-bin-win-cuda-13.4-arm64.zip)
- [Windows x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b12065/llama-b12065-bin-win-vulkan-x64.zip)
- [Windows arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b12065/llama-b12065-bin-win-vulkan-arm64.zip)
- [Windows x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b12065/llama-b12065-bin-win-openvino-2026.4.1-x64.zip)
- [Windows x64 (SYCL)](https://github.com/ggml-org/llama.cpp/releases/download/b12065/llama-b12065-bin-win-sycl-x64.zip)
- [Windows x64 (ROCm 10.0)](https://github.com/ggml-org/llama.cpp/releases/download/b12065/llama-b12065-bin-win-rocm-10.0-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/b12065/llama-b12065-ui.tar.gz)