neuron-tai/.scratch/distributed-gguf-runtime/evidence/DGR-001/README.md

DGR-001 — performance contract baseline

Files changed

• packages/node/meshnet_node/performance_contract.py
• tests/test_performance_contract.py
• .scratch/distributed-gguf-runtime/issues/01-lock-the-safetensors-versus-gguf-performance-contract.md
• .scratch/distributed-gguf-runtime/evidence/DGR-001/performance-contract.json

What this slice does

• Locks the DGR-001 benchmark contract in code.
• Pins the architecture-aligned baseline to DeepSeek-V2-Lite-Chat (deepseek2).
• Uses the same model on both sides of the comparison:
  • safetensors: deepseek-ai/DeepSeek-V2-Lite-Chat in BF16
  • GGUF: second-state/DeepSeek-V2-Lite-Chat-GGUF in Q2_K
• Exposes a machine-readable JSON contract with:
  • benchmark lanes for transformers safetensors and llama.cpp GGUF on CPU and GPU
  • concurrency levels 1 and 4
  • the required metrics list
  • an explicit stop condition for “no meaningful speed or fit benefit”
• Adds a deterministic stub benchmark report so the contract now has an executable report shape end to end.

Recent benchmark runner slice

The runner currently uses a deterministic stub backend to exercise the comparison matrix without downloading a model. It emits:

• .scratch/distributed-gguf-runtime/evidence/DGR-001/performance-contract.json
• .scratch/distributed-gguf-runtime/evidence/DGR-001/stub-benchmark-report.json

The report includes per-device comparisons for:

• transformers-safetensors-cpu vs llama-cpp-gguf-cpu
• transformers-safetensors-gpu vs llama-cpp-gguf-gpu

and records the memory metric (rss_bytes on CPU, vram_bytes on GPU), decode speedup, artifact ratio, and output drift.

Exact commands and real results

Targeted tests

pytest -q tests/test_performance_contract.py tests/test_route_session_benchmark.py

Result: 9 passed in 0.14s

Contract artifact generation

PYTHONPATH=packages/node python -m meshnet_node.performance_contract --json-out .scratch/distributed-gguf-runtime/evidence/DGR-001/performance-contract.json

Result: wrote .scratch/distributed-gguf-runtime/evidence/DGR-001/performance-contract.json

Python compile check

python -m compileall packages/node/meshnet_node/performance_contract.py tests/test_performance_contract.py

Result: passed

Limitations

• This slice captures the DGR-001 contract and baseline selection only.
• It does not download or run a real model yet.
• Real safetensors vs GGUF execution, TTFT/prefill/decode measurements, RSS/VRAM capture, and output-drift comparison are still to be implemented against the contract.

Compatibility notes

• The contract stays on the DeepSeek2 family to remain close to the DeepSeek-V4-Flash end goal.
• A smaller non-DeepSeek model can still be used later for loader-plumbing smoke tests, but it does not replace this baseline.
• Model artifacts must stay on the mounted drive and not under /home.

Dependent-story handoff

Next implementation work should attach to this contract and add the live benchmark runner that actually compares:

1. current Transformers/safetensors recipe
2. whole-model llama.cpp GGUF recipe

using the same model architecture/revision and the same prompt/context/concurrency settings.