ZIP
WinGet
llama.cpp
ggml · b9085 · x64
Before deploying, verify this file with VirusTotal ↗
Silent Commands
Distributed as a ZIP archive — extract the contents and run the executable directly. No installer is included.
File Identity
Filename
llama-b9085-bin-win-vulkan-x64.zip
Signature
Status
Upload installer to verify signature
Installer Selection
WinGet Package
Package ID
ggml.llamacpp
Version
b9085
Description
LLM inference in C/C++
License
MIT
↗
Installer URL
https://github.com/ggml-org/llama.cpp/releases/download/b9085/llama-b9085-bin-win-vulkan-x64.zip
Release Notes
Add flash attention MMA / Tiles to support MiMo-V2.5 (#22812)
- mimo-v2.5: add flash attention mma/tiles for for d_kq=192 d_v=128
- mimo-v2.5: follow (256, 256) fattn templates
- mimo-v2.5: cleanup comments
- mimo-v2.5: further comment cleanup
- mimo-v2.5: address PR feedback
fix GQA handling
check for other dangling 320/576 carveouts and mirror them for 192
Add to backend ops test so new paths are covered
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enab…