AISpot

llama.cpp 用 171 個真實 HF 倉庫鎖定 GGUF 解析測試

llama.cpp releases版本更新地端推論開源

llama.cpp 建置 b11900 把模型解析測試固定在真實 HuggingFace 倉庫佈局上,test-model-resolution 現覆蓋 171 個遵循 GGUF 命名約定(小寫 sidecar 字首、短橫線分隔、量化型別在末尾)的倉庫清單。測試從 1174 個主流發布者的 GGUF 倉庫中提取每種檔案佈局模式,每個倉庫都鎖定當前 master 的解析計劃與快取列表,出現不匹配時會集中報告為解析 bug。不符合命名約定的倉庫被剔除;

原標題:b11900
閱讀原文

評分42 / 40(平均 41,門檻 60)
狀態未入選

原文

common: pin model resolution on real HF repo layouts ( #30548 ) tests: pin model resolution on real repo listings Extend test-model-resolution with 63 repo listings captured verbatim from the HF API, chosen to cover every file naming pattern found across 1237 GGUF repos of the major publishers and pruned to whole quant groups. Each repo pins its resolved plans and its cache listing. The expectations follow what each file really is per its GGUF header, not what the current resolver picks, so a mismatch is a resolution bug. Mismatches are collected and reported together before the test fails. tests: leave the listing unchecked on paths the filesystem refuses Some real split names (DevQuasar's Model.Q2_K.gguf-00001-of-00012.gguf under a quant folder) exceed MAX_PATH once materialized in the temporary cache on Windows, so the listing of such a repo is skipped with a note while its plans stay checked. tests: pin real listings to master on GGUF convention names only Replace the real repo table with 171 HF listings whose file names follow the GGUF naming convention (lowercase sidecar prefix, - delimited components, quant last), one per layout pattern found across 1174 GGUF repos and pruned to whole quant groups. Repos outside the convention are dropped. Each repo pins the plans and the cache listing master gives today, so the test is a pure harness: any change in resolution shows up here, and mismatches are reported together. Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/59940447 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45

b11536: ui: Models Manager Follow-up Improvements (#30228)

llama.cpp 新版本 b11536 讓 server 的 GET /models 直接返回每個模型的訓練上下文長度(context_length),資料取自 GGUF 後設資料,無需載入模型或請求 Hugging Face Hub。新增的 common_get_gguf_n_ctx_train 只讀後設資料、相容 u32 與 u64,檔案缺失或無效時返回 0,router 列表因此可離線攜帶該欄位。

llama.cpp releasesAI 評分41

llama.cpp 的 GGUF 寫入器跳過主機張量暫存複製

llama.cpp 合併 ggml 改動(#31144):GGUF 寫入器此前會把每個張量先拷進臨時 vector 再寫檔案,現在對 host-buffer 張量直接寫盤,省去逐張量的分配、零初始化與 memcpy。這是建置期最佳化,不改變 GGUF 格式,同時隨附 macOS、Linux、Windows、Android 等平台建置產物清單。

llama.cpp releases● 精選AI 評分78

llama.cpp UI 新增 Discover,可瀏覽下載 HuggingFace GGUF 並斷點續傳

llama.cpp 的圖形介面新增 Discover Models 檢視,可直接在應用內瀏覽並下載 HuggingFace 上的 GGUF 模型,由 Enable Discover Models 開關控制。下載支援暫停與續傳:暫停後保留已下載的分片檔案,重啟或重新開啟後仍能接著磁碟上的進度繼續。下載項按倉庫聚類,主權重會順帶拉取匹配的 draft sidecar(DFlash 優先於 MTP)以啟用投機解碼,決策模型等無法執行的模型已從目錄與搜尋中過濾。