# ggerganov/llama.cpp b9413: b9413 — retained record

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

Canonical: https://highsignal.app/data/records/bd0484ea4404482d

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


source: [github](https://highsignal.app/data/github) (github:ggerganov/llama.cpp)  published 2026-05-29 18:42 ingested 2026-05-30 08:26

[original source ↗](https://github.com/ggml-org/llama.cpp/releases/tag/b9413)

## extract

<details open>

CUDA: Check PTX version on host side to guard PDL dispatch (#23530)

* CUDA: Check PTX version on host side to guard PDL dispatch

Checking on `__CUDA_ARCH_LIST__` alone is insufficient for JIT, as this
variable doesn't differentiate between compiling for say sm_90, sm_90a
or sm_90f (so forward-jittable PTX vs. arch/family-specific PTX).

Thus, one can have a bug when compiling with
`DCMAKE_CUDA_ARCHITECTURES="89;90a"`, where current code would wrongly
dispatch to PDL on sm_90/sm_120 in forward-JIT mode.

This PR fixes this issue by checking `cudaFuncAttributes::ptxVersion` of
the incoming kernel at runtime. A check on ptxVersion alone is
sufficient, as device-codes will always be >= ptxVersion (and any
violation of this would be a severe bug in CUDA/nvcc), see:
 https://docs.nvidia.com/cuda/cuda-compiler-driver-nvcc/#gpu-code-code-code

* Implement MurmurHash3 mixer for better hash distribution

Magic constants were taken from boost:
https://github.com/boostorg/container_hash/blob/2698b43803c012601e6bb1a6116e83767b97986c/include/boost/container_hash/detail/hash_mix.hpp#L19-L65

* Update ggml/src/ggml-cuda/common.cuh

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

* Address review comments, make seed non-zero

* Apply code-formatting

* Replace std::size_t -> size_t for consistency

---------

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

</details>

**macOS/iOS:**
- [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b9413/llama-b9413-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/b9413/llama-b9413-bin-macos-x64.tar.gz)
- [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b9413/llama-b9413-xcframework.zip)

**Linux:**
- [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9413/llama-b9413-bin-ubuntu-x64.tar.gz)
- [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9413/llama-b9413-bin-ubuntu-arm64.tar.gz)
- [Ubuntu s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9413/llama-b9413-bin-ubuntu-s390x.tar.gz)
- [Ubuntu x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b9413/llama-b9413-bin-ubuntu-vulkan-x64.tar.gz)
- [Ubuntu arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b9413/llama-b9413-bin-ubuntu-vulkan-arm64.tar.gz)
- [Ubuntu x64 (ROCm 7.2)](https://github.com/ggml-org/llama.cpp/releases/download/b9413/llama-b9413-bin-ubuntu-rocm-7.2-x64.tar.gz)
- [Ubuntu x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b9413/llama-b9413-bin-ubuntu-openvino-2026.0-x64.tar.gz)
- Ubuntu x64 (SYCL FP32) [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23705)

**Android:**
- [Android arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9413/llama-b9413-bin-android-arm64.tar.gz)

**Windows:**
- [Windows x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9413/llama-b9413-bin-win-cpu-x64.zip)
- [Windows arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9413/llama-b9413-bin-win-cpu-arm64.zip)
- [Windows x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/b9413/llama-b9413-bin-win-cuda-12.4-x64.zip) - [CUDA 12.4 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b9413/cudart-llama-bin-win-cuda-12.4-x64.zip)
- [Windows x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b9413/llama-b9413-bin-win-cuda-13.3-x64.zip) - [CUDA 13.3 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b9413/cudart-llama-bin-win-cuda-13.3-x64.zip)
- [Windows x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b9413/llama-b9413-bin-win-vulkan-x64.zip)
- Windows x64 (SYCL) [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23705)
- [Windows x64 (HIP)](https://github.com/ggml-org/llama.cpp/releases/download/b9413/llama-b9413-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/b9413/llama-b9413-ui.tar.gz)

## retained text

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