# ggerganov/llama.cpp b8966: b8966 — retained record

> Retained github record from github:ggerganov/llama.cpp.

Canonical: https://highsignal.app/data/records/8bbe73712cafe707

[← sources](https://highsignal.app/data)


source: [github](https://highsignal.app/data/github) (github:ggerganov/llama.cpp)  published 2026-04-28 20:35 ingested 2026-04-29 08:10

[original source ↗](https://github.com/ggml-org/llama.cpp/releases/tag/b8966)

## extract

<details open>

ggml-cuda: add flash-attn support for DKQ=320/DV=256 with ncols2=32 (… (#22286)

* ggml-cuda: add flash-attn support for DKQ=320/DV=256 with ncols2=32 (GQA=32)

Adds MMA-f16 and tile kernel configs, dispatch logic, template instances,
and tile .cu file for Mistral Small 4 (head sizes 320/256), restricting to
ncols2=32 to support GQA ratio 32 only.

* Adding check to return BEST_FATTN_KERNEL_NONE in case GQA!=32

* Apply suggestions from code review

Address review comments

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>

* Address review comments and making kernel config default to DQK=512, DV=512 instead of DQK=256,DV=256

* Fixed bug with sinks=1, with ncols=32, there are two warp-groups created but sinks index is same(0,...,15) for both the groups hence with sinks=1, output is not matching with CPU output. Added sink_base which will be base index for each warp_group (threadIdx.y / np)

* Apply suggestions from code review

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>

* Update ggml/src/ggml-cuda/template-instances/generate_cu_files.py

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>

---------

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>

</details>

**macOS/iOS:**
- [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b8966/llama-b8966-bin-macos-arm64.tar.gz)
- [macOS Apple Silicon (arm64, KleidiAI enabled)](https://github.com/ggml-org/llama.cpp/releases/download/b8966/llama-b8966-bin-macos-arm64-kleidiai.tar.gz)
- [macOS Intel (x64)](https://github.com/ggml-org/llama.cpp/releases/download/b8966/llama-b8966-bin-macos-x64.tar.gz)
- [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b8966/llama-b8966-xcframework.zip)

**Linux:**
- [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b8966/llama-b8966-bin-ubuntu-x64.tar.gz)
- [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b8966/llama-b8966-bin-ubuntu-arm64.tar.gz)
- [Ubuntu s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b8966/llama-b8966-bin-ubuntu-s390x.tar.gz)
- [Ubuntu x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b8966/llama-b8966-bin-ubuntu-vulkan-x64.tar.gz)
- [Ubuntu arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b8966/llama-b8966-bin-ubuntu-vulkan-arm64.tar.gz)
- [Ubuntu x64 (ROCm 7.2)](https://github.com/ggml-org/llama.cpp/releases/download/b8966/llama-b8966-bin-ubuntu-rocm-7.2-x64.tar.gz)
- [Ubuntu x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b8966/llama-b8966-bin-ubuntu-openvino-2026.0-x64.tar.gz)
- [Ubuntu x64 (SYCL FP32)](https://github.com/ggml-org/llama.cpp/releases/download/b8966/llama-b8966-bin-ubuntu-sycl-fp32-x64.tar.gz)
- [Ubuntu x64 (SYCL FP16)](https://github.com/ggml-org/llama.cpp/releases/download/b8966/llama-b8966-bin-ubuntu-sycl-fp16-x64.tar.gz)

**Android:**
- [Android arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b8966/llama-b8966-bin-android-arm64.tar.gz)

**Windows:**
- [Windows x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b8966/llama-b8966-bin-win-cpu-x64.zip)
- [Windows arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b8966/llama-b8966-bin-win-cpu-arm64.zip)
- [Windows x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/b8966/llama-b8966-bin-win-cuda-12.4-x64.zip) - [CUDA 12.4 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b8966/cudart-llama-bin-win-cuda-12.4-x64.zip)
- [Windows x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b8966/llama-b8966-bin-win-cuda-13.1-x64.zip) - [CUDA 13.1 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b8966/cudart-llama-bin-win-cuda-13.1-x64.zip)
- [Windows x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b8966/llama-b8966-bin-win-vulkan-x64.zip)
- [Windows x64 (SYCL)](https://github.com/ggml-org/llama.cpp/releases/download/b8966/llama-b8966-bin-win-sycl-x64.zip)
- [Windows x64 (HIP)](https://github.com/ggml-org/llama.cpp/releases/download/b8966/llama-b8966-bin-win-hip-radeon-x64.zip)

**openEuler:**
- [openEuler x86 (310p)](https://github.com/ggml-org/llama.cpp/releases/download/b8966/llama-b8966-bin-310p-openEuler-x86.tar.gz)
- [openEuler x86 (910b, ACL Graph)](https://github.com/ggml-org/llama.cpp/releases/download/b8966/llama-b8966-bin-910b-openEuler-x86-aclgraph.tar.gz)
- [openEuler aarch64 (310p)](https://github.com/ggml-org/llama.cpp/releases/download/b8966/llama-b8966-bin-310p-openEuler-aarch64.tar.gz)
- [openEuler aarch64 (910b, ACL Graph)](https://github.com/ggml-org/llama.cpp/releases/download/b8966/llama-b8966-bin-910b-openEuler-aarch64-aclgraph.tar.gz)

## retained text

No document body was retained for this record — only its metadata was stored.
