AISpot

llama.cpp b11922 修正多序列回放與 partial state 測試

llama.cpp releases版本更新地端推論開源開發工具

llama.cpp 發布 b11922,主要修正是讓多序列 split replay 與 partial state 的測試在已訓練模型上成立。原測試中回滾快照與參考上下文的 batch 形狀不同,狀態末位差異會被模型逐 token 放大;現在只比較每條序列的首個重放 token,並在 seq-1 的 tail 前把回滾狀態載回參考上下文。

原標題:b11922
閱讀原文

評分35 / 38(平均 36,門檻 60)
狀態未入選

原文

tests : fix multi-seq split replay and partial-state cases for trained models ( #31216 ) tests : fix multi-seq split replay against trained models The rollback snapshot is captured by the graph that decoded the rolled-back tail, while the reference context decodes the same prefix with different batch shapes. The two states differ in the last bits and trained models amplify the difference with every replayed token. Compare only the first replayed token of each seq, then restore the rollback state into the reference context before the seq-1-only tail. Assisted-by: dsh:llama.cpp/ggml-org/Qwen3.8-Flash-Next-GGUF (MacBook, M5 Max, 128GB) tests : require bit-exact seq-1 isolation in split replay The seq state save is not always bit-lossless - SWA-masked cells are not saved - so reload the restored state back into the rollback context. That way both contexts enter the seq-1-only tail with byte-identical memory, including the cell layout, and the tail logits must match bit-exact. Also assert that the restored state round-trips bit-identical. Assisted-by: dsh:llama.cpp/ggml-org/Qwen3.8-Flash-Next-GGUF (MacBook, M5 Max, 128GB) tests : drop the n_swa partial-state check from ps The check keys off llama_model_n_swa(), which returns 0 for dsv4 even though its raw KV cache has a 128-cell sliding window. The partial state grows with the tokens there by design, so the flatness check is wrong. Keep the partial <= full invariant. Assisted-by: dsh:llama.cpp/ggml-org/Qwen3.8-Flash-Next-GGUF (MacBook, M5 Max, 128GB) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/60276548 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux: Ubuntu x64 (CPU) Ubuntu arm64 (CPU) Ubuntu s390x (CPU) Ubuntu x64 (Vulkan) Ubuntu arm64 (Vulkan) Ubuntu x64 (CUDA 12) - CUDA 12.8 libraries Ubuntu x64 (CUDA 13) - CUDA 13.4 libraries Ubuntu arm64 (CUDA 13) - CUDA 13.4 libraries Ubuntu x64 (ROCm 10.0) Ubuntu x64 (OpenVINO) Ubuntu x64 (SYCL FP32) Ubuntu x64 (SYCL FP16) Linux arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide Android: Android arm64 (CPU) Android arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide Windows: Windows x64 (CPU) Windows arm64 (CPU) Windows arm64 (OpenCL Adreno) Windows x64 (CUDA 12) - CUDA 12.4 DLLs Windows x64 (CUDA 13) - CUDA 13.4 DLLs Windows arm64 (CUDA 13) - CUDA 13.4 DLLs Windows x64 (Vulkan) Windows arm64 (Vulkan) Windows x64 (OpenVINO) Windows x64 (SYCL) Windows x64 (ROCm 10.0) openEuler: DISABLED openEuler x86 (310p) openEuler x86 (910b, ACL Graph) openEuler aarch64 (310p) openEuler aarch64 (910b, ACL Graph) UI: UI

相關報導

llama.cpp releasesAI 評分36

llama.cpp 測試提速:模型儲存不再建立 llama_context

llama.cpp 建置 b11934 最佳化了測試流程,重構 save_models 使其只建立模型而不再建立儲存時用不到的 llama_context,並用 splitmix64 加 Box-Muller 生成器替換較慢的 std::normal_distribution 抽樣。張量資料改為用 std::mt19937 預先生成一組正態抽樣池,各張量按名稱迴圈取切片,保證結果確定;每次儲存模型後還會輸出檔名、目標路徑與位元組/MB 體積。

llama.cpp releasesAI 評分40

llama.cpp 建置 b11577 修復 vllm 多序列用例

llama.cpp 發布建置 b11577,主要修復 vllm 的 d3 多序列用例(#30408),並留下一處 TODO。同一批建置覆蓋 macOS Apple Silicon 與 Intel、iOS XCFramework、Linux、Android、Windows 與 openEuler,後端含 CPU、Vulkan、CUDA 12(12.4 DLLs)與 CUDA 13(13.4 DLLs)、ROCm 10.0、OpenVINO 與 SYCL,Snapdragon 版…

llama.cpp releasesAI 評分37

llama.cpp 發布 b11465,覆蓋 CUDA 13 與 ROCm 10.0 等平台

llama.cpp 發布建置版本 b11465,本次改動是「測試:在測試遞迴回滾時保留 anchor」(#29923)。該版本提供的預編譯產物覆蓋 macOS/iOS、Linux、Android、Windows 與 openEuler,其中 Windows 與 Linux 的 x64/arm64 均包含 CUDA 12、CUDA 13(CUDA 13.4 庫)、Vulkan、ROCm 10.0、OpenVINO、SYCL 等後端。