Starstruk Logo MarkStarstruk

b9970

ggml-org/llama.cppb9970Jul 12, 2026by github-actions[bot]

AI Summary

Introduces a new `GGML_OP_LIGHTNING_INDEXER` operation to implement the lightning indexer for DeepSeek V3.2 and V4 models, along with comprehensive tests and RPC updates.

Key Highlights

  • Added `GGML_OP_LIGHTNING_INDEXER` operation to ggml
  • Integrated lightning indexer into DeepSeek V3.2 and V4 models
  • Added tests for mask broadcasting and FLOPs calculation
  • Bumped RPC version to support the new operation

New Features

  • GGML_OP_LIGHTNING_INDEXER operation
  • DeepSeek V3.2/V4 lightning indexer support

Full Release Notes

<details open>

ggml : add GGML_OP_LIGHTNING_INDEXER that implements DeepSeek V3.2/V4 lightning indexer (#24231)

* ggml : add GGML_OP_LIGHTNING_INDEXER that implements DeepSeek V3.2/V4 lightning indexer

* ggml : remove scale parameters from lightning indexer OP, add f16 mask parameter

* tests : add GGML_OP_LIGHTNING_INDEXER tests

* ggml : bump RPC version

* chore : check if lightning indexer input tensors are not transposed

* tests : count flops instead of bandwidth in lightning indexer test

* chore : add missing const

* chore : whitespace

* ggml : renamed variables in CPU lightning indexer implementation

* ggml : fix lightning indexer mask broadcasting

* tests : tests for lightning indexer mask broadcasting

* chore : whitespace

* llama : use GGML_OP_LIGHTNING_INDEXER in DeepSeek V3.2 and DeepSeek V4 models

---------

Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com>

</details>

**macOS/iOS:**
- [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b9970/llama-b9970-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/b9970/llama-b9970-bin-macos-x64.tar.gz)
- [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b9970/llama-b9970-xcframework.zip)

**Linux:**
- [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9970/llama-b9970-bin-ubuntu-x64.tar.gz)
- [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9970/llama-b9970-bin-ubuntu-arm64.tar.gz)
- [Ubuntu s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9970/llama-b9970-bin-ubuntu-s390x.tar.gz)
- [Ubuntu x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b9970/llama-b9970-bin-ubuntu-vulkan-x64.tar.gz)
- [Ubuntu arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b9970/llama-b9970-bin-ubuntu-vulkan-arm64.tar.gz)
- [Ubuntu x64 (ROCm 7.2)](https://github.com/ggml-org/llama.cpp/releases/download/b9970/llama-b9970-bin-ubuntu-rocm-7.2-x64.tar.gz)
- [Ubuntu x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b9970/llama-b9970-bin-ubuntu-openvino-2026.2.1-x64.tar.gz)
- [Ubuntu x64 (SYCL FP32)](https://github.com/ggml-org/llama.cpp/releases/download/b9970/llama-b9970-bin-ubuntu-sycl-fp32-x64.tar.gz)
- [Ubuntu x64 (SYCL FP16)](https://github.com/ggml-org/llama.cpp/releases/download/b9970/llama-b9970-bin-ubuntu-sycl-fp16-x64.tar.gz)

**Android:**
- [Android arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9970/llama-b9970-bin-android-arm64.tar.gz)

**Windows:**
- [Windows x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9970/llama-b9970-bin-win-cpu-x64.zip)
- [Windows arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9970/llama-b9970-bin-win-cpu-arm64.zip)
- [Windows arm64 (OpenCL Adreno)](https://github.com/ggml-org/llama.cpp/releases/download/b9970/llama-b9970-bin-win-opencl-adreno-arm64.zip)
- [Windows x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/b9970/llama-b9970-bin-win-cuda-12.4-x64.zip) - [CUDA 12.4 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b9970/cudart-llama-bin-win-cuda-12.4-x64.zip)
- [Windows x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b9970/llama-b9970-bin-win-cuda-13.3-x64.zip) - [CUDA 13.3 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b9970/cudart-llama-bin-win-cuda-13.3-x64.zip)
- [Windows x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b9970/llama-b9970-bin-win-vulkan-x64.zip)
- [Windows x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b9970/llama-b9970-bin-win-openvino-2026.2.1-x64.zip)
- [Windows x64 (SYCL)](https://github.com/ggml-org/llama.cpp/releases/download/b9970/llama-b9970-bin-win-sycl-x64.zip)
- [Windows x64 (HIP)](https://github.com/ggml-org/llama.cpp/releases/download/b9970/llama-b9970-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/b9970/llama-b9970-ui.tar.gz)