Khaled Bakeer

TandemLLM

TandemLLM began as an inference engine and grew into the environment around it. A request goes in, a router reads what it wants, and the model gets the skills, memory and sandboxed tools that kind of task needs. Underneath, small drafters guess the next tokens and the big model checks the guesses in one pass. A guess it agrees with is a free token. What comes out is the model's own text, only faster. Nothing in the design depends on one model or one machine.

More about TandemLLM

The path of one request

1. RoutingA router reads the request, decides what kind of task it is and how much reasoning it deserves.
2. Skills and memoryThe task gets the skills and packages written for it, and notes from earlier sessions when memory is on.
3. Sandboxed toolsShell, files, web and MCP servers run in a sandbox that belongs to this one conversation, behind permission prompts.
4. State cachesThe KV and recurrent state of the last turn is still there for the next one, in memory or on disk, so a long conversation resumes instead of reading it all again.
5. Draft and verifySmall drafters propose a tree of tokens. The big model checks the whole tree in one pass and keeps every guess it agrees with.
6. MonitorWhile the model writes, the conductor reads along. It closes a reasoning loop, repairs a broken tool call and checks each call against its schema.