Richard Loyer 3a5f735ab9 Optim prefill: ngl99/t8/b512=49.9 t/s (+11%), full offload, decode CPU		2026-05-24 16:35:52 +02:00
.gitignore	Engine cadrage: CLAUDE.md analyse R&D, verdict NPU-prefill/CPU-decode	2026-05-24 12:34:14 +02:00
CLAUDE.md	Optim prefill: ngl99/t8/b512=49.9 t/s (+11%), full offload, decode CPU	2026-05-24 16:35:52 +02:00