{ "schema_version": 1, "contract_version": 1, "contract_id": "dgr-alpha-beta-performance/v1", "locked_at": "2026-07-22", "locked_by": "DGR-019", "locked_before_target_execution": true, "prompt_set": { "id": "dgr-fixed-prompt-set-v1", "prompts": [ { "id": "short-instruction", "text": "Summarize the following changelog entry in one sentence: Added distributed layer-range execution for GGUF shards using range-aware tensor ownership.", "context_class": "short" }, { "id": "code-completion", "text": "def fibonacci(n):\n \"\"\"Return the nth Fibonacci number.\"\"\"\n", "context_class": "short" }, { "id": "multi-step-reasoning", "text": "A route has three shards, each holding a contiguous layer range. If shard A owns layers 0-13, shard B owns layers 14-27, and shard C owns layers 28-42, how many layers does each shard own and which shard is the tail?", "context_class": "short" }, { "id": "long-context-fill", "text": "Repeat the phrase 'the route holds a contiguous layer range' 1024 times, then answer: which node owns the tail?", "context_class": "long", "notes": "Beta long-context lane only; the driver expands this template to the locked context_tokens length rather than the literal text carrying that many tokens in this document." } ] }, "sampling": { "temperature": 0.0, "top_p": 1.0, "top_k": 1, "seed": 1234, "notes": "Greedy by construction, matching meshnet_node.recipe_benchmark.SamplingPolicy defaults: sampling noise must never be indistinguishable from a quantization, transport, or batching effect." }, "lanes": { "controlled-safetensors": { "role": "reference recipe", "locked_elsewhere": true, "contract_module": "meshnet_node.performance_contract", "contract_id": "dgr-001-controlled-whole-model-baseline-v1", "contract_schema_version": 1, "notes": "Already locked by DGR-001/performance_contract.py (contract_version=1, immutable ContractThresholds). This document does not re-lock or duplicate those thresholds; it references them so the four lanes are enumerated in one place." }, "whole-model-gguf": { "role": "single-node quantization/model-fit comparison against controlled-safetensors", "locked_elsewhere": true, "contract_module": "meshnet_node.performance_contract", "contract_id": "dgr-001-controlled-whole-model-baseline-v1", "contract_schema_version": 1, "notes": "Same locked contract as controlled-safetensors; this is the reference recipe's counterpart lane, not a separate threshold set." }, "dense-distributed-gguf": { "role": "multi-shard Meshnet Inference Route running a dense (non-MoE) architecture's GGUF weights across a real multi-machine route via the ShardEngine/native worker", "reference_baseline": "the existing production Meshnet distributed Route Session running the same dense model over safetensors on the same node topology and network", "prompt_ids": [ "short-instruction", "code-completion", "multi-step-reasoning" ], "context_tokens": 2048, "output_tokens": 128, "concurrency_levels": [ 1, 4 ], "hardware": { "topology": "named certification scenario only: 2-4-stage or 10-plus-stage real multi-machine route", "network": "same LAN/WAN class as the existing production route it is compared against", "device_class": "generic; not hardcoded to one backend. CPU/CUDA/ROCm/Vulkan/Metal lanes are certified separately per RALPH-CONTEXT.md and only advertised once real-hardware-certified" }, "metrics": [ "ttft_p50_ms", "ttft_p95_ms", "prefill_tokens_per_sec", "decode_tokens_per_sec", "aggregate_decode_tokens_per_sec", "latency_p50_ms", "latency_p95_ms", "seam_bytes", "seam_latency_ms", "queue_wait_ms", "peak_rss_bytes", "peak_vram_bytes", "failures" ], "certification_scenarios": { "stage_count": [ "2-4-stage", "10-plus-stage" ], "quantization": [ "Q4_K_M", "Q8_0", "bf16-reference" ] } }, "v4-flash-distributed": { "role": "full DeepSeek V4 Flash (43 main layers plus reserved MTP; mHC 4x4096 boundary; 256 routed + 1 shared experts, six routed active) distributed route across a named certification stage-count scenario, MTP reserved and off", "reference_baseline": "the existing production Meshnet distributed Route Session running DeepSeek V4 Flash over safetensors on the same node topology and network, where available; otherwise dense-distributed-gguf runtime/transport overhead is reported as an explicit limitation until DGR-044 pins a safetensors V4 baseline", "prompt_ids": [ "short-instruction", "code-completion", "multi-step-reasoning" ], "alpha_context_tokens": 4096, "alpha_output_tokens": 128, "alpha_concurrency_levels": [ 1, 4 ], "beta_context_tokens": 16384, "beta_output_tokens": 512, "beta_concurrency_levels": [ 1, 4, 8, 16 ], "beta_prompt_ids": [ "short-instruction", "code-completion", "multi-step-reasoning", "long-context-fill" ], "hardware": { "topology": "named certification scenario only: 2-4-stage or 10-plus-stage real multi-machine route", "network": "same LAN/WAN class as the existing production route it is compared against", "device_class": "generic; not hardcoded to one backend. CPU/CUDA/ROCm/Vulkan/Metal lanes are certified separately per RALPH-CONTEXT.md and only advertised once real-hardware-certified", "mtp": "reserved and off for alpha; ownership contract, implementation, and benchmark are required before beta per RALPH-CONTEXT.md" }, "metrics": [ "ttft_p50_ms", "ttft_p95_ms", "prefill_tokens_per_sec", "decode_tokens_per_sec", "aggregate_decode_tokens_per_sec", "latency_p50_ms", "latency_p95_ms", "seam_bytes", "seam_latency_ms", "queue_wait_ms", "peak_rss_bytes", "peak_vram_bytes", "failures", "mtp_enabled" ], "certification_scenarios": { "stage_count": [ "2-4-stage", "10-plus-stage" ], "quantization": [ "Q4_K_M", "Q8_0", "bf16-reference" ] } } }, "gain_attribution": { "quantization_model_fit_metrics": [ "resident_memory_ratio", "artifact_size_ratio", "exact_match_rate", "mean_similarity", "peak_rss_bytes", "peak_vram_bytes" ], "runtime_transport_batching_kernel_metrics": [ "decode_speedup", "ttft_ratio", "aggregate_throughput_speedup", "seam_bytes", "seam_latency_ms", "queue_wait_ms", "prefill_tokens_per_sec" ], "rule": "A speed or fit claim must cite which axis moved it: a quantization/model-fit change (recipe swap, weight format) or a runtime/transport/batching/kernel change (ShardEngine, gRPC transport, batching, GGML kernel). A distributed-lane win may not be attributed to quantization when the reference recipe already used the same quantization, and a quantization win may not be attributed to distribution or transport." }, "certification_scenarios": { "quantization": { "names": [ "Q4_K_M", "Q8_0", "bf16-reference" ], "rule": "Named certification-scenario labels only. No product or runtime code path may branch on, default to, or hardcode a specific quantization string; quantization is a dynamic recipe input per RALPH-CONTEXT.md." }, "stage_count": { "names": [ "2-4-stage", "10-plus-stage" ], "rule": "Named certification-scenario labels only, matching DGR-053/DGR-061/DGR-062/DGR-067. No product or runtime code path may hardcode a stage-count range or assume exactly one of these layouts." } }, "alpha": { "applies_to_lane": "v4-flash-distributed", "reference_baseline_lane": "dense-distributed-gguf", "correctness": { "min_greedy_token_agreement": 0.9, "min_mean_state_cosine_similarity": 0.999, "forbid_nonfinite_tensors": true, "require_fail_closed_on_fingerprint_mismatch": true, "require_active_moe_routing": true, "require_active_hash_routing_first_three_layers": true, "dense_attention_fallback_satisfies_alpha": false }, "useful_speed": { "min_decode_speedup_vs_reference_baseline": 1.25, "max_ttft_ratio_vs_reference_baseline": 1.25, "min_aggregate_throughput_speedup_at_top_concurrency": 1.25, "quality_pass_with_speed_fail_verdict": "stop", "human_approval": { "required": true, "approved": false, "approved_by": null, "approved_at": null, "approval_note": "The ratios above are the proposed useful-speed floor, held at the same 25% margin already locked for the whole-model contract (DGR-001/v1, meshnet_node.performance_contract.ContractThresholds). Alpha certification (DGR-054) may not treat useful-speed as satisfied on ratios alone: a human must explicitly approve the observed ratio against real DGR-020/dense/V4 evidence, and this record is the audit trail for that approval." } }, "mtp": { "reserved": true, "enabled_for_alpha": false, "ownership_contract_and_benchmark_required_before_beta": true }, "failure_tolerance": { "max_failure_rate": 0.0 }, "verdicts": [ "alpha", "optimize", "stop" ], "stop_condition": "Stop DeepSeek V4 Flash alpha certification when correctness fails (greedy token agreement, mean state cosine similarity, nonfinite tensors, or fail-closed fingerprint checks), or when useful-speed is not both numerically satisfied and explicitly human-approved against the reference baseline lane under this plan. A quality pass with a speed fail is always 'stop', never 'optimize' — see performance.quality_pass_with_speed_fail_verdict." }, "beta": { "applies_to_lane": "v4-flash-distributed", "adds": [ "concurrency", "long_context", "failure", "sustained_throughput" ], "concurrency": { "levels": [ 1, 4, 8, 16 ], "min_aggregate_throughput_speedup_at_max_concurrency": 1.25, "max_fairness_deviation": 0.2 }, "long_context": { "context_tokens": 16384, "min_greedy_token_agreement": 0.9, "max_ttft_seconds_at_context": 600 }, "failure": { "consecutive_clean_cold_starts": 2, "require_worker_loss_aborts_route": true, "require_cache_miss_and_reprefill_on_route_change": true, "forbid_silent_kv_migration": true, "synthetic_workers_satisfy_beta": false }, "sustained_throughput": { "min_duration_minutes": 30, "max_throughput_degradation_ratio": 0.1 }, "verdicts": [ "beta", "targeted-optimization", "stop-rollback" ], "stop_condition": "Stop or roll back DeepSeek V4 Flash beta when any beta-only threshold fails (concurrency fairness/throughput, long-context correctness or TTFT, failure-recovery semantics, or sustained-throughput degradation), when a required stage-count or quantization certification scenario has no real-hardware evidence, or when MTP evidence is missing given MTP is required before beta per RALPH-CONTEXT.md." }, "amendment_policy": "Thresholds are locked before target execution and may not be weakened, moved, or reinterpreted after results are known. A change requires a new contract_id and contract_version under human review, and the superseded contract is retained. This applies independently of alpha.useful_speed.human_approval, which records sign-off on an observed ratio against these unchanged thresholds, not a change to the thresholds themselves.", "contract_sha256": "cb5a482a8f142bf45b1dd401743d408acbfe5f85bab86023144a8c9485ac6379" }