Starstruk Logo MarkStarstruk

b10032

ggml-org/llama.cppb10032Jul 15, 2026by github-actions[bot]

AI Summary

Adds a new CUDA implementation for the lightning indexer operation using generic vector and WMMA kernels, with architectural relaxations and refactoring.

Key Highlights

  • CUDA GGML_OP_LIGHTNING_INDEXER implementation (generic vector kernel + wmma kernel)
  • Relaxed MMA architecture requirements to Turing
  • Added alignment checks for Q and K tensors
  • Template parameters added to avoid duplication of constants

New Features

  • New CUDA kernel for lightning indexing
  • Optimized tensor alignment handling

Full Release Notes

<details open>

cuda : CUDA GGML_OP_LIGHTNING_INDEXER implementation (generic vector kernel + wmma kernel) (#25545)

* cuda : CUDA GGML_OP_LIGHTNING_INDEXER implementation (generic vector kernel + wmma kernel)

* chore : remove indentation of #pragma unroll

* cuda : remove unnecessary kernel template declarations

* cuda : add WARPS_PER_BLOCK and K_VECS_PER_BLOCK template parameters in lightning indexer kernels to avoid duplication of constants.

* cuda : relax MMA architecture requirements to Turing in lightning indexer implementation

* chore : renamed variables

* chore : rename ggml_cuda_op_lightning_indexer() to ggml_cuda_lightning_indexer()

* chore : TODO for AMD rocWMMA

* chore : whitespace formatting

* chore : another variable rename to fix problems caused by shadowing

* chore : yet another rename, this time uppercased all constants

* cuda : added alignment checks for Q and K tensors in lightning indexer implementation

---------

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

</details>

**macOS/iOS:**
- [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b10032/llama-b10032-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/b10032/llama-b10032-bin-macos-x64.tar.gz)
- [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b10032/llama-b10032-xcframework.zip)

**Linux:**
- [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10032/llama-b10032-bin-ubuntu-x64.tar.gz)
- [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10032/llama-b10032-bin-ubuntu-arm64.tar.gz)
- [Ubuntu s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10032/llama-b10032-bin-ubuntu-s390x.tar.gz)
- [Ubuntu x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b10032/llama-b10032-bin-ubuntu-vulkan-x64.tar.gz)
- [Ubuntu arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b10032/llama-b10032-bin-ubuntu-vulkan-arm64.tar.gz)
- [Ubuntu x64 (ROCm 7.2)](https://github.com/ggml-org/llama.cpp/releases/download/b10032/llama-b10032-bin-ubuntu-rocm-7.2-x64.tar.gz)
- [Ubuntu x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b10032/llama-b10032-bin-ubuntu-openvino-2026.2.1-x64.tar.gz)
- [Ubuntu x64 (SYCL FP32)](https://github.com/ggml-org/llama.cpp/releases/download/b10032/llama-b10032-bin-ubuntu-sycl-fp32-x64.tar.gz)
- [Ubuntu x64 (SYCL FP16)](https://github.com/ggml-org/llama.cpp/releases/download/b10032/llama-b10032-bin-ubuntu-sycl-fp16-x64.tar.gz)

**Android:**
- [Android arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10032/llama-b10032-bin-android-arm64.tar.gz)

**Windows:**
- [Windows x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10032/llama-b10032-bin-win-cpu-x64.zip)
- [Windows arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10032/llama-b10032-bin-win-cpu-arm64.zip)
- [Windows arm64 (OpenCL Adreno)](https://github.com/ggml-org/llama.cpp/releases/download/b10032/llama-b10032-bin-win-opencl-adreno-arm64.zip)
- [Windows x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/b10032/llama-b10032-bin-win-cuda-12.4-x64.zip) - [CUDA 12.4 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b10032/cudart-llama-bin-win-cuda-12.4-x64.zip)
- [Windows x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b10032/llama-b10032-bin-win-cuda-13.3-x64.zip) - [CUDA 13.3 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b10032/cudart-llama-bin-win-cuda-13.3-x64.zip)
- [Windows x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b10032/llama-b10032-bin-win-vulkan-x64.zip)
- [Windows x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b10032/llama-b10032-bin-win-openvino-2026.2.1-x64.zip)
- [Windows x64 (SYCL)](https://github.com/ggml-org/llama.cpp/releases/download/b10032/llama-b10032-bin-win-sycl-x64.zip)
- [Windows x64 (HIP)](https://github.com/ggml-org/llama.cpp/releases/download/b10032/llama-b10032-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/b10032/llama-b10032-ui.tar.gz)