b9893

<details open>

opencl: general flash attention decode performance optimizations (#25366)

* opencl: vec flash-attention decode kernels for f16/q8_0/q4_0 KV

* opencl: improve non FA KQ mv kernels

* opencl: tweaks for multiquery FA

* opencl: some tweaks for FA q1 kernels

* opencl: FA with DK=DV=512 for gemma-4

* opencl: various fixes

* opencl: cleanup

* opencl: fix FA decode crash for DK=512 (gemma-4)

The DK=512 decode-only program does not create the f32_f16 prefill
kernel, so the compiled check in ensure_fa_variant never hit and
supports_op gave inconsistent answers for the same op. block_n is also
unset for DK=512 decode; guard it to avoid an out-of-range read at
dispatch.

* opencl: run DK=512 FA decode on CPU

DK=512 decode is bandwidth-bound and faster on the CPU than the GPU,
increasingly so with depth. Decline it in supports_op; prefill stays on the GPU.

* opencl: compile MQ_GQA=8 FA kernels in a minimal program

The full program compiled with -D MQ_GQA=8 runs the Adreno compiler out
of memory at DK>=256. Only the vec_mq kernels are used from this
program, so compile it with FA_MQ_ONLY, which excludes everything else.
Also include the program name in the compile error log.

* opencl: remove stray token in flash_attn_f32_f16.cl

A stray "." broke the f32_f16 program build.

* opencl: split f16-KV FA decode finer (FD_KV_PER_SPLIT_F16)

The 2048 default under-fills the GPU on single-query f16-KV decode;
use 512 for f16 KV to get more splits. Quantized KV keeps 2048.

---------

Co-authored-by: Li He <lih@qti.qualcomm.com>

</details>

**macOS/iOS:**
- [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b9893/llama-b9893-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/b9893/llama-b9893-bin-macos-x64.tar.gz)
- [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b9893/llama-b9893-xcframework.zip)

**Linux:**
- [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9893/llama-b9893-bin-ubuntu-x64.tar.gz)
- [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9893/llama-b9893-bin-ubuntu-arm64.tar.gz)
- [Ubuntu s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9893/llama-b9893-bin-ubuntu-s390x.tar.gz)
- [Ubuntu x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b9893/llama-b9893-bin-ubuntu-vulkan-x64.tar.gz)
- [Ubuntu arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b9893/llama-b9893-bin-ubuntu-vulkan-arm64.tar.gz)
- [Ubuntu x64 (ROCm 7.2)](https://github.com/ggml-org/llama.cpp/releases/download/b9893/llama-b9893-bin-ubuntu-rocm-7.2-x64.tar.gz)
- [Ubuntu x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b9893/llama-b9893-bin-ubuntu-openvino-2026.2.1-x64.tar.gz)
- [Ubuntu x64 (SYCL FP32)](https://github.com/ggml-org/llama.cpp/releases/download/b9893/llama-b9893-bin-ubuntu-sycl-fp32-x64.tar.gz)
- [Ubuntu x64 (SYCL FP16)](https://github.com/ggml-org/llama.cpp/releases/download/b9893/llama-b9893-bin-ubuntu-sycl-fp16-x64.tar.gz)

**Android:**
- [Android arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9893/llama-b9893-bin-android-arm64.tar.gz)

**Windows:**
- [Windows x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9893/llama-b9893-bin-win-cpu-x64.zip)
- [Windows arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9893/llama-b9893-bin-win-cpu-arm64.zip)
- [Windows arm64 (OpenCL Adreno)](https://github.com/ggml-org/llama.cpp/releases/download/b9893/llama-b9893-bin-win-opencl-adreno-arm64.zip)
- [Windows x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/b9893/llama-b9893-bin-win-cuda-12.4-x64.zip) - [CUDA 12.4 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b9893/cudart-llama-bin-win-cuda-12.4-x64.zip)
- [Windows x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b9893/llama-b9893-bin-win-cuda-13.3-x64.zip) - [CUDA 13.3 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b9893/cudart-llama-bin-win-cuda-13.3-x64.zip)
- [Windows x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b9893/llama-b9893-bin-win-vulkan-x64.zip)
- [Windows x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b9893/llama-b9893-bin-win-openvino-2026.2.1-x64.zip)
- [Windows x64 (SYCL)](https://github.com/ggml-org/llama.cpp/releases/download/b9893/llama-b9893-bin-win-sycl-x64.zip)
- [Windows x64 (HIP)](https://github.com/ggml-org/llama.cpp/releases/download/b9893/llama-b9893-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/b9893/llama-b9893-ui.tar.gz)