Files
neuron-tai/.scratch/distributed-gguf-runtime/issues/03-prefill-decode-wire-protocol.md
2026-07-07 15:27:33 +03:00

759 B

03 — Prefill/decode wire protocol

Status: ready-for-agent

Goal

Define and implement the activation protocol needed by both PyTorch and future GGUF backends.

Scope

  • Add route/session lifecycle headers.
  • Separate prefill from decode-step.
  • Keep binary bfloat16 activation bodies.
  • Preserve relay compatibility.
  • Add route id and model artifact hash validation.

Draft Endpoints

  • POST /sessions/{session_id}/prefill
  • POST /sessions/{session_id}/decode-step
  • DELETE /sessions/{session_id}
  • GET /sessions/{session_id}/status

Acceptance

  • Old /forward remains temporarily or fails with clear version message.
  • Tests cover relay preservation of session headers.
  • Decode-step payload is independent of prompt length.