36 lines
1.4 KiB
Markdown
36 lines
1.4 KiB
Markdown
# Distributed GGUF runtime milestones
|
|
|
|
## Gate A — measured runtime value
|
|
|
|
- DGR-001 locks the safetensors-versus-GGUF performance/fit/quality contract.
|
|
- DGR-002 can proceed independently and defines the battle-proven backend-neutral wire protocol.
|
|
- DGR-003 builds exact recipe identity on DGR-002.
|
|
- Expensive native llama.cpp work remains gated by DGR-001.
|
|
|
|
## Gate B — minimal native execution seam
|
|
|
|
- DGR-004 creates the reproducible pinned fork boundary.
|
|
- DGR-005 implements dense-Llama range ownership.
|
|
- DGR-006 proves architecture-defined boundary parity.
|
|
|
|
## Gate C — concurrent production worker
|
|
|
|
- DGR-007 isolates concurrent Hot KV State.
|
|
- DGR-008 exposes the native worker over gRPC.
|
|
- DGR-009 integrates the worker without replacing Meshnet's control plane.
|
|
- DGR-010 passes local real-model two-process acceptance.
|
|
|
|
## Gate D — real consumer-hardware route
|
|
|
|
- DGR-011 passes two-physical-machine execution.
|
|
- DGR-012 adds continuous batching and bounded admission.
|
|
- DGR-013 hardens failure and cancellation.
|
|
|
|
## Gate E — product release decision
|
|
|
|
- DGR-014 compares distributed GGUF against the current distributed safetensors route under locked thresholds.
|
|
- DGR-015 adds Qwen3/Qwen3-MoE only after the dense runtime passes.
|
|
- DGR-016 prepares narrow upstream llama.cpp collaboration material.
|
|
|
|
No later gate may be claimed from synthetic workers or documentation-only evidence.
|