b10236

ggml-org/llama.cppb10236Aug 3, 2026by github-actions[bot]

AI Summary

Implemented a Lightning Indexer for DeepSeek V4 in Metal, optimized with tiled kernels and staged memory access, resulting in significant performance improvements for large context lengths.

Key Highlights

Implemented GGML_OP_LIGHTNING_INDEXER for DeepSeek V4.
Performance improvements of up to 20% for prefix pass at 10k context length.
Supports various quantization types (F32, F16, BF16, Q4, Q5, Q8) for K caches.

New Features

Metal Lightning Indexer implementation
Optimized tiled kernels for large KV caches

Full Release Notes

<details open>

metal: implement DSv4 Lightning Indexer (#25893)

* metal: implement F16 Lightning Indexer

- Implement GGML_OP_LIGHTNING_INDEXER for 128-dimensional, 64-head inputs
  with F32 queries and weights plus F16 keys and masks.
- Add tiled and tail kernels and test KV lengths around 8- and 64-element
  boundaries.

llama-bench (--mmap 1, -fa 1, -p 512, -n 128; d=0/10k/20k/30k):

Before:
- pp512: 153.73 ± 0.87 t/s
- tg128: 8.91 ± 0.04 t/s
- pp512 @ d10000: 73.90 ± 0.39 t/s
- tg128 @ d10000: 8.66 ± 0.03 t/s
- pp512 @ d20000: 45.83 ± 0.18 t/s
- tg128 @ d20000: 8.26 ± 0.03 t/s
- pp512 @ d30000: 33.40 ± 0.21 t/s
- tg128 @ d30000: 7.94 ± 0.01 t/s

After:
- pp512: 155.19 ± 0.91 t/s
- tg128: 8.95 ± 0.04 t/s
- pp512 @ d10000: 86.95 ± 0.69 t/s
- tg128 @ d10000: 9.00 ± 0.05 t/s
- pp512 @ d20000: 62.01 ± 0.45 t/s
- tg128 @ d20000: 8.68 ± 0.04 t/s
- pp512 @ d30000: 49.18 ± 0.33 t/s
- tg128 @ d30000: 8.60 ± 0.02 t/s

Assisted-by: Codex

* metal: stage Lightning Indexer K tiles

- Stage and dequantize K in F16 threadgroup memory before simdgroup matrix loads.
- Zero-fill partial tiles and guard stores so all KV segments use the same numerical path.
- Support F32, F16, BF16, Q4_0, Q4_1, Q5_0, Q5_1, and Q8_0 K caches.

llama-bench (--mmap 1, -fa on, -p 512, -n 128; d=0/10k/20k):

- pp512: 160.38 +/- 1.01 t/s
- tg128: 9.08 +/- 0.03 t/s
- pp512 @ d10000: 88.37 +/- 0.46 t/s
- tg128 @ d10000: 9.07 +/- 0.04 t/s
- pp512 @ d20000: 62.53 +/- 0.46 t/s
- tg128 @ d20000: 8.84 +/- 0.03 t/s

Assisted-by: Codex

* dedup Lightning Indexer constants, fix flaky test

* cont : fix whitespace

---------

Co-authored-by: forforever73 <690105611@qq.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

</details>

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

**macOS/iOS:**
- [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b10236/llama-b10236-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/b10236/llama-b10236-bin-macos-x64.tar.gz)
- [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b10236/llama-b10236-xcframework.zip)

**Linux:**
- [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10236/llama-b10236-bin-ubuntu-x64.tar.gz)
- [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10236/llama-b10236-bin-ubuntu-arm64.tar.gz)
- [Ubuntu s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10236/llama-b10236-bin-ubuntu-s390x.tar.gz)
- [Ubuntu x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b10236/llama-b10236-bin-ubuntu-vulkan-x64.tar.gz)
- [Ubuntu arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b10236/llama-b10236-bin-ubuntu-vulkan-arm64.tar.gz)
- [Ubuntu x64 (ROCm 7.2)](https://github.com/ggml-org/llama.cpp/releases/download/b10236/llama-b10236-bin-ubuntu-rocm-7.2-x64.tar.gz)
- [Ubuntu x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b10236/llama-b10236-bin-ubuntu-openvino-2026.2.1-x64.tar.gz)
- [Ubuntu x64 (SYCL FP32)](https://github.com/ggml-org/llama.cpp/releases/download/b10236/llama-b10236-bin-ubuntu-sycl-fp32-x64.tar.gz)
- [Ubuntu x64 (SYCL FP16)](https://github.com/ggml-org/llama.cpp/releases/download/b10236/llama-b10236-bin-ubuntu-sycl-fp16-x64.tar.gz)

**Android:**
- [Android arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10236/llama-b10236-bin-android-arm64.tar.gz)

**Windows:**
- [Windows x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10236/llama-b10236-bin-win-cpu-x64.zip)
- [Windows arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10236/llama-b10236-bin-win-cpu-arm64.zip)
- [Windows arm64 (OpenCL Adreno)](https://github.com/ggml-org/llama.cpp/releases/download/b10236/llama-b10236-bin-win-opencl-adreno-arm64.zip)
- [Windows x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/b10236/llama-b10236-bin-win-cuda-12.4-x64.zip) - [CUDA 12.4 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b10236/cudart-llama-bin-win-cuda-12.4-x64.zip)
- [Windows x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b10236/llama-b10236-bin-win-cuda-13.3-x64.zip) - [CUDA 13.3 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b10236/cudart-llama-bin-win-cuda-13.3-x64.zip)
- [Windows x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b10236/llama-b10236-bin-win-vulkan-x64.zip)
- [Windows x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b10236/llama-b10236-bin-win-openvino-2026.2.1-x64.zip)
- [Windows x64 (SYCL)](https://github.com/ggml-org/llama.cpp/releases/download/b10236/llama-b10236-bin-win-sycl-x64.zip)
- [Windows x64 (HIP)](https://github.com/ggml-org/llama.cpp/releases/download/b10236/llama-b10236-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/b10236/llama-b10236-ui.tar.gz)