Maarufu: Data ilisasishwa 27 Oktoba 2026

Kategoria

Intaneti1,356
Mawasiliano321
Sauti na video898
Michoro na usanifu539
Ofisi na tija1,124
Zana za wasanidi3,134
Zana za AI529
Usalama na faragha385
Zana za mfumo3,114
Michezo523
Elimu na sayansi239
Mtandao na TEHAMA284

Pakua llama.cpp b7973

LLM inference in C/C++

Hili ni toleo la zamani. Toleo la sasa ni b9994. llama.cpp b9994 · Lilitolewa:

Faili za kisakinishi b7973

UsanifuAinaUpeoUkubwa wa failiPakuaSHA256
64-bit ZIP → Portable — — github.com VirusTotal

Kiungo na SHA256 vinatoka kwenye manifest ya jumuiya ya Windows Package Manager. Linganisha hashi ya faili uliyopakua kabla ya kuiendesha.

Maelezo ya toleo

[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)

https://github.com/ggml-org/llama.cpp/releases/tag/b7973

Lebo

Shiriki