Olala (by OVH), a MoE that can run on CPU
Run OVHai's Olala mini, a hybrid Mamba-3 MoE model, on CPU only with its llama.cpp fork inside a Docker Sandboxes (sbx) environment.
Badges come from GitHub once the author claims this feed.
Run OVHai's Olala mini, a hybrid Mamba-3 MoE model, on CPU only with its llama.cpp fork inside a Docker Sandboxes (sbx) environment.
Understand the Agent Client Protocol: how a code editor and a coding agent talk over JSON-RPC and stdio, from initialize to permissions and cancellation.
Connect VS Code over SSH to an sbx sandbox built from kits, for a devcontainer-like workflow with microVM isolation, secrets protection and network policies.