本文へ移動
AI NEWS JOURNAL
llama.cpp releasesAI NEWS / JOURNAL

b12549

The llama.cpp v1.25.49 release includes fixes for Inkling 2 attention mask handling, making the relative-position input a hybrid iswa input, enabling optional expert weight scale and final logit softcap, and improving KV rows mask generation for hybrid iswa memory. The update also standardizes code formatting in inkling2.cpp and ensures compatibility across multiple platforms including macOS, Linux, Windows, Android, and openEuler.

翻訳サービスが停止中のため原文を表示しています。

<details open> llama: fixes for Inkling 2 attention mask (#32429) * llama : give Inkling2 its own relative-position attention input The Inkling2 graph built its flash attention mask from the hybrid iswa input and passed it to build_attn through a new kq_mask argument. That argument let a caller pair its own dense mask with the kv_rows of llm_graph_input_attn_kv_iswa, whose mask follows the per-sequence cell lists whenever kv_rows is enabled. Add llm_graph_input_attn_rel_pos instead. It owns dense KQ masks and the query-to-cell distances, fills both from the same cells, and its build_attn overload adds the per-head bias to its own mask and never passes kv_rows. The iswa build_attn is back to its previous signature; its body moves to build_attn_iswa_impl, which both overloads call. Inkling2 now folds the per-query sink into the bias with and without flash attention, so build_attn_mha no longer needs the per-query sink path. Assisted-By: Claude Opus 5.5 <noreply@anthropic.com> * inkling2 : make the expert weight scale and final logit softcap optional Load both keys as optional and skip them when they are zero, as other models do, instead of rejecting zero at load. Assisted-By: Claude Opus 5.5 <noreply@anthropic.com> * llama : build kv_rows masks for the hybrid iswa memory llm_graph_input_mem_hybrid_iswa checked its masks with can_reuse_attn_mask, which expects kv_rows whenever they are enabled, but built them dense. With a unified cache and flash attention the check always failed, and hybrid iswa models (LFM2, LFM3, Inkling2) never reused a graph. Build the masks with build_attn_inp_attn_mask, like the plain iswa input. Assisted-By: Claude Opus 5.5 <noreply@anthropic.com> * llama : make the relative-position input a hybrid iswa input Address review: llm_graph_input_mem_hybrid_iswa_rel derives from llm_graph_input_mem_hybrid_iswa and owns the attention and recurrent inputs, so Inkling2 builds one memory input instead of two. Its attention input is built with dense masks, can_reuse checks them as dense, and its build_attn asserts that the mask has no kv_rows (TODO: a kv_rows variant). build_attn_iswa_impl is now a static helper. Assisted-By: Claude Opus 5.5 <noreply@anthropic.com> * llama : compose the hybrid iswa rel input, format inkling2 Address review: llm_graph_input_mem_hybrid_iswa_rel owns its attention and recurrent inputs like the other composite inputs instead of deriving from llm_graph_input_mem_hybrid_iswa. Format src/models/inkling2.cpp like the other model sources: grouped and aligned key and tensor loading, descriptive per-layer names, blank lines and section comments between the steps, and cb() names for the intermediate tensors. The graph is unchanged. Assisted-By: Claude Opus 5.5 <noreply@anthropic.com> </details> **Website:** - <https://llama.app> **Attestations:** - <https://github.com/ggml-org/llama.cpp/attestations/69772952> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b12549/llama-b12549-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/b12549/llama-b12549-bin-macos-x64.tar.gz) - [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b12549/llama-b12549-xcframework.zip) **Linux:** - [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b12549/llama-b12549-bin-ubuntu-x64.tar.gz) - [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b12549/llama-b12549-bin-ubuntu-arm64.tar.gz) - [Ubuntu 24.04 s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b12549/llama-b12549-bin-ubuntu-s390x.tar.gz) - [Ubuntu 26.04 s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b12549/llama-b12549-bin-ubuntu-26.04-s390x.tar.gz) - [Ubuntu 26.04 s390x (zDNN)](https://github.com/ggml-org/llama.cpp/releases/download/b12549/llama-b12549-bin-ubuntu-zdnn-s390x.tar.gz) - [Ubuntu x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b12549/llama-b12549-bin-ubuntu-vulkan-x64.tar.gz) - [Ubuntu arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b12549/llama-b12549-bin-ubuntu-vulkan-arm64.tar.gz) - [Ubuntu x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/b12549/llama-b12549-bin-ubuntu-cuda-12.8-x64.tar.gz) - [CUDA 12.8 libraries](https://github.com/ggml-org/llama.cpp/releases/download/b12549/cudart-llama-b12549-bin-ubuntu-cuda-12.8-x64.tar.gz) - [Ubuntu x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b12549/llama-b12549-bin-ubuntu-cuda-13.5-x64.tar.gz) - [CUDA 13.5 libraries](https://github.com/ggml-org/llama.cpp/releases/download/b12549/cudart-llama-b12549-bin-ubuntu-cuda-13.5-x64.tar.gz) - [Ubuntu arm64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b12549/llama-b12549-bin-ubuntu-cuda-13.5-arm64.tar.gz) - [CUDA 13.5 libraries](https://github.com/ggml-org/llama.cpp/releases/download/b12549/cudart-llama-b12549-bin-ubuntu-cuda-13.5-arm64.tar.gz) - [Ubuntu x64 (ROCm 10.0)](https://github.com/ggml-org/llama.cpp/releases/download/b12549/llama-b12549-bin-ubuntu-rocm-10.0-x64.tar.gz) - [Ubuntu x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b12549/llama-b12549-bin-ubuntu-openvino-2026.4.1-x64.tar.gz) - [Ubuntu x64 (SYCL FP32)](https://github.com/ggml-org/llama.cpp/releases/download/b12549/llama-b12549-bin-ubuntu-sycl-fp32-x64.tar.gz) - [Ubuntu x64 (SYCL FP16)](https://github.com/ggml-org/llama.cpp/releases/download/b12549/llama-b12549-bin-ubuntu-sycl-fp16-x64.tar.gz) - [Linux arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU)](https://github.com/ggml-org/llama.cpp/releases/download/b12549/llama-b12549-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/b12549/llama-b12549-bin-android-arm64.tar.gz) - [Android arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU)](https://github.com/ggml-org/llama.cpp/releases/download/b12549/llama-b12549-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/b12549/llama-b12549-bin-win-cpu-x64.zip) - [Windows arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b12549/llama-b12549-bin-win-cpu-arm64.zip) - [Windows arm64 (OpenCL Adreno)](https://github.com/ggml-org/llama.cpp/releases/download/b12549/llama-b12549-bin-win-opencl-adreno-arm64.zip) - [Windows x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/b12549/llama-b12549-bin-win-cuda-12.4-x64.zip) - [CUDA 12.4 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b12549/cudart-llama-bin-win-cuda-12.4-x64.zip) - [Windows x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b12549/llama-b12549-bin-win-cuda-13.5-x64.zip) - [CUDA 13.5 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b12549/cudart-llama-bin-win-cuda-13.5-x64.zip) - [Windows arm64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b12549/llama-b12549-bin-win-cuda-13.5-arm64.zip) - [CUDA 13.5 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b12549/cudart-llama-bin-win-cuda-13.5-arm64.zip) - [Windows x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b12549/llama-b12549-bin-win-vulkan-x64.zip) - [Windows arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b12549/llama-b12549-bin-win-vulkan-arm64.zip) - [Windows x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b12549/llama-b12549-bin-win-openvino-2026.4.1-x64.zip) - [Windows x64 (SYCL)](https://github.com/ggml-org/llama.cpp/releases/download/b12549/llama-b12549-bin-win-sycl-x64.zip) - [Windows x64 (ROCm 10.0)](https://github.com/ggml-org/llama.cpp/releases/download/b12549/llama-b12549-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/b12549/llama-b12549-ui.tar.gz)

出典

原文を読む ↗

関連テーマ

← すべてのニュースへ