Skip to content

v0.6.2

Latest
Latest

Choose a tag to compare

View all tags
@primoco primoco released this 09 Jun 16:26
· 5 commits to main since this release
EuLLM-v0.6.2
09ff027
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

EULLM Engine EuLLM-v0.6.2

Drop-in Ollama replacement with continuous batching and EU AI Act audit trail.

Quick install

# Linux x64 (CPU only)
curl -L https://github.com/eullm/eullm/releases/download/EuLLM-v0.6.2/eullm-linux-x64 -o eullm
chmod +x eullm

# Linux x64 with NVIDIA GPU (CUDA 12.8 — supports RTX 3000/4000/5000 series)
curl -L https://github.com/eullm/eullm/releases/download/EuLLM-v0.6.2/eullm-linux-x64-cuda-12.8 -o eullm
chmod +x eullm

# macOS Apple Silicon
curl -L https://github.com/eullm/eullm/releases/download/EuLLM-v0.6.2/eullm-macos-arm64 -o eullm
chmod +x eullm
# Windows x64 (CPU only) — PowerShell
Invoke-WebRequest -Uri https://github.com/eullm/eullm/releases/download/EuLLM-v0.6.2/eullm-windows-x64.exe -OutFile eullm.exe

# Windows x64 with NVIDIA GPU (CUDA 12.8 — supports RTX 3000/4000/5000)
# This is a ZIP: eullm.exe + the CUDA runtime DLLs it needs.
Invoke-WebRequest -Uri https://github.com/eullm/eullm/releases/download/EuLLM-v0.6.2/eullm-windows-x64-cuda-12.8.zip -OutFile eullm-cuda.zip
Expand-Archive eullm-cuda.zip -DestinationPath eullm-cuda
# Run eullm.exe from inside the extracted folder (the DLLs must
# stay next to it).
.\eullm-cuda\eullm.exe run model.gguf

Which binary to download?

Binary GPU Support Requirements
eullm-linux-x64 CPU only None
eullm-linux-x64-cuda-12.8 NVIDIA GPU (RTX 3000/4000/5000) NVIDIA driver 570+
eullm-linux-arm64 CPU only ARM64 Linux
eullm-macos-x64 CPU only macOS Intel
eullm-macos-arm64 Metal (Apple GPU) macOS Apple Silicon
eullm-windows-x64.exe CPU only Windows 10/11 x64
eullm-windows-x64-cuda-12.8.zip NVIDIA GPU (RTX 3000/4000/5000) NVIDIA driver 570+ for Windows. ZIP bundles eullm.exe + CUDA DLLs — run from the extracted folder

Pick a model interactively

# Run with no arguments to open the model picker (local models + catalog)
./eullm

Web browsing

# Enable transparent web fetch (URLs in messages are fetched and injected)
./eullm run model.gguf --web

Usage

./eullm run ./model.gguf                    # Run any GGUF model
./eullm run ./model.gguf --batch-size 16    # Continuous batching for RAG
./eullm run ./model.gguf --web              # Enable web browsing

Verify checksums

sha256sum -c checksums.txt

What's Changed

Full Changelog: EuLLM-v0.6.1...EuLLM-v0.6.2

Contributors

primoco
Assets 10
Loading