Serve thousands of per-customer LoRA adapters on one base 8B, sharing KV cache where you can.
Each customer has their own LoRA on a shared 8B. The S-LoRA-style answer keeps one base in memory, pages adapters in and out, and tags every KV block with an adapter ID so reuse never crosses tenants.
Updated Aug 2026 · Grounded in real Forward Deployed Engineer interview loops and written to a senior-engineer editorial bar.
Each customer has their own LoRA on a shared 8B. The S-LoRA-style answer keeps one base in memory, pages adapters in and out, and tags every KV block with an adapter ID so reuse never crosses tenants.
Lead with where the obvious approach breaks, because that is the judgment they are screening for — most candidates jump straight to the happy path and lose the room.
Then walk the failure back through the pipeline in order, naming the one metric the customer's exec sponsor actually cares about before you propose the fix.
