← sources

ggerganov/llama.cpp b9509: b9509

source: github (github:ggerganov/llama.cpp)published 2026-06-04 13:53ingested 2026-06-05 09:36

retained text

<details open>

server: avoid unnecessary checkpoint restore when new tokens are present (#24110)

* server: avoid unnecessary checkpoint restore when new tokens are present

The pos_min_thold calculation unconditionally subtracts 1 to ensure at
least one token is evaluated for logits when no new tokens exist.
However, when the request contains new tokens beyond the cached prefix,
this -1 is overly conservative and may trigger an unnecessary checkpoint
restore.

Conditionally apply the -1 only when n_past >= task.n_tokens() (no new
tokens), avoiding redundant KV state restoration when there is actual
work to do.

* cont : add ref

---------

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

</details>

**macOS/iOS:**
- [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b9509/llama-b9509-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/b9509/llama-b9509-bin-macos-x64.tar.gz)
- [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b9509/llama-b9509-xcframework.zip)

**Linux:**
- [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9509/llama-b9509-bin-ubuntu-x64.tar.gz)
- [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9509/llama-b9509-bin-ubuntu-arm64.tar.gz)
- [Ubuntu s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9509/llama-b9509-bin-ubuntu-s390x.tar.gz)
- [Ubuntu x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b9509/llama-b9509-bin-ubuntu-vulkan-x64.tar.gz)
- [Ubuntu arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b9509/llama-b9509-bin-ubuntu-vulkan-arm64.tar.gz)
- [Ubuntu x64 (ROCm 7.2)](https://github.com/ggml-org/llama.cpp/releases/download/b9509/llama-b9509-bin-ubuntu-rocm-7.2-x64.tar.gz)
- [Ubuntu x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b9509/llama-b9509-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/b9509/llama-b9509-bin-android-arm64.tar.gz)

**Windows:**
- [Windows x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9509/llama-b9509-bin-win-cpu-x64.zip)
- [Windows arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9509/llama-b9509-bin-win-cpu-arm64.zip)
- [Windows x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/b9509/llama-b9509-bin-win-cuda-12.4-x64.zip) - [CUDA 12.4 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b9509/cudart-llama-bin-win-cuda-12.4-x64.zip)
- [Windows x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b9509/llama-b9509-bin-win-cuda-13.3-x64.zip) - [CUDA 13.3 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b9509/cudart-llama-bin-win-cuda-13.3-x64.zip)
- [Windows x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b9509/llama-b9509-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/b9509/llama-b9509-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/b9509/llama-b9509-ui.tar.gz)

document fetched 2026-06-05 09:36