# ggerganov/llama.cpp b9479: b9479 — retained record

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

Canonical: https://highsignal.app/data/records/beaf966295e13c71

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


source: [github](https://highsignal.app/data/github) (github:ggerganov/llama.cpp)  published 2026-06-02 14:20 ingested 2026-06-03 10:50

[original source ↗](https://github.com/ggml-org/llama.cpp/releases/tag/b9479)

## retained text



```
<details open>

common : fix state save in common_prompt_batch_decode (#23468)

* common : fix state save in common_prompt_batch_decode

This commit addresses a bug in common_prompt_batch_decode that affects
the session state store/restore in completion.cpp and
save-load-state.cpp.

The motivation for this is that currently the code is saving n-1 tokens
in both the session_tokens and in the KV cache. Then when loading the
session tokens, and if the prompt matches, it would replay the last
saved token (n-1) into the next position, effectively replaying the
same token in the wrong position.

The fix is to store all n tokens in session_tokens, while the memory
state only reflects n-1 processed tokens as the saving happens before
the last token is decoded in common_prompt_batch_decode.

I ran both completion.cpp and save-load-state.cpp with a transformer, a
recurrent, and a hybrid model.

Resolves: https://github.com/ggml-org/llama.cpp/issues/23400

Co-authored-by: fairydreaming <166155368+fairydreaming@users.noreply.github.com>

</details>

**macOS/iOS:**
- [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b9479/llama-b9479-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/b9479/llama-b9479-bin-macos-x64.tar.gz)
- [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b9479/llama-b9479-xcframework.zip)

**Linux:**
- [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9479/llama-b9479-bin-ubuntu-x64.tar.gz)
- [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9479/llama-b9479-bin-ubuntu-arm64.tar.gz)
- [Ubuntu s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9479/llama-b9479-bin-ubuntu-s390x.tar.gz)
- [Ubuntu x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b9479/llama-b9479-bin-ubuntu-vulkan-x64.tar.gz)
- [Ubuntu arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b9479/llama-b9479-bin-ubuntu-vulkan-arm64.tar.gz)
- [Ubuntu x64 (ROCm 7.2)](https://github.com/ggml-org/llama.cpp/releases/download/b9479/llama-b9479-bin-ubuntu-rocm-7.2-x64.tar.gz)
- [Ubuntu x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b9479/llama-b9479-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/b9479/llama-b9479-bin-android-arm64.tar.gz)

**Windows:**
- [Windows x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9479/llama-b9479-bin-win-cpu-x64.zip)
- [Windows arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9479/llama-b9479-bin-win-cpu-arm64.zip)
- [Windows x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/b9479/llama-b9479-bin-win-cuda-12.4-x64.zip) - [CUDA 12.4 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b9479/cudart-llama-bin-win-cuda-12.4-x64.zip)
- [Windows x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b9479/llama-b9479-bin-win-cuda-13.3-x64.zip) - [CUDA 13.3 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b9479/cudart-llama-bin-win-cuda-13.3-x64.zip)
- [Windows x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b9479/llama-b9479-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/b9479/llama-b9479-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/b9479/llama-b9479-ui.tar.gz)
```



document fetched 2026-06-03 10:50
