Questa è una versione precedente. La versione attuale è la b9994. llama.cpp b9994 · Data di rilascio:
File di installazione b7973
| Architettura | Tipo | Ambito | Dimensione | Scarica | SHA256 |
|---|---|---|---|---|---|
| 64 bit | ZIP → Portable | — | — | github.com | VirusTotal |
Link e hash SHA256 provengono dal manifest della community di Gestione pacchetti Windows. Prima di eseguire il file scaricato conviene confrontarne l’hash.
Note di rilascio
[Model] Qwen3.5 dense and MoE support (no vision) (#19435)
- Unified delta net handling
- Remove old methods.
- Refactor and optimize
- Adapt autoregressive version from @ymcki
- Change to decay mask approach
- Fix bad permute
- Qwen 3.5 support
- Apply suggestions from code review
Co-authored-by: Sigbjørn Skjæret sigbjorn.skjaeret@scala.com
- Further fixes
- Use inheritance, remove unneeded conts
- Not like this!
- Remove ggml.h explicit import
- Remove transformers, fix the views
- ACTUALLY fix views, make super calls explicit in conversion.
- Fix conversion again
- Remove extra ggml.h imports
Co-authored-by: Sigbjørn Skjæret sigbjorn.skjaeret@scala.com
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)