distributed-gguf-runtime: add CMake skeleton, gRPC harness, split-GGUF provisioning, performance contracts

DGR-019 Lock alpha/beta performance contracts (evidence + contract framework) DGR-020 Run controlled whole-model GGUF baseline (benchmark results & contracts) DGR-024 Real generated-gRPC protocol harness (shard_runtime_server.py + tests) DGR-026 split-GGUF provisioning outside /home (provision script + manifest + tests) DGR-028 Numbered patch-stack apply & verify (llama_cpp_dependency.py + UPSTREAM_LOCK.json) DGR-029 Native CMake skeleton + deterministic CPU lane (UPSTREAM_LOCK.json + cmake gating) New modules: packages/node/meshnet_node/dgr_performance/ — performance contract framework packages/node/meshnet_node/split_gguf/ — split-GGUF manifest & provisioning scripts/provision_split_gguf.py — artifact provisioning CLI tests/test_dgr_performance_contract.py — contract validation tests tests/test_split_gguf_manifest.py — manifest tests tests/test_split_gguf_provision.py — provisioning tests tests/test_shard_runtime_harness.py — gRPC harness tests
2026-07-23 09:55:00 +03:00
parent 47bad0b7e1
commit 966aa10854
36 changed files with 7225 additions and 374 deletions
--- a/.scratch/distributed-gguf-runtime/evidence/DGR-020/performance-contract.json
+++ b/.scratch/distributed-gguf-runtime/evidence/DGR-020/performance-contract.json
@@ -0,0 +1,87 @@
+{
+  "schema_version": 1,
+  "contract_version": 1,
+  "locked_at": "2026-07-13T00:00:00Z",
+  "locked_by": "DGR-001",
+  "plan_id": "dgr-001-controlled-whole-model-baseline-v1",
+  "thresholds": {
+    "min_decode_speedup": 1.25,
+    "max_ttft_ratio": 1.25,
+    "min_aggregate_throughput_speedup": 1.25,
+    "max_resident_memory_ratio": 0.75,
+    "max_artifact_size_ratio": 0.6,
+    "min_quality_exact_match_rate": 0.9,
+    "min_quality_mean_similarity": 0.97,
+    "max_failure_rate": 0.0
+  },
+  "baseline": {
+    "status": "pending-real-evidence",
+    "required_evidence_class": "local-real",
+    "required_recipes": [
+      "transformers-safetensors-reference",
+      "llama-cpp-near-lossless-quality",
+      "llama-cpp-quantized-performance-fit"
+    ],
+    "required_concurrency_levels": [
+      1,
+      4
+    ],
+    "required_controlled_variables": [
+      "model architecture",
+      "model revision",
+      "machine and device",
+      "formatted prompts and context lengths",
+      "output length and greedy sampling policy"
+    ],
+    "required_plan_sha256": "efe24690a9a7164bac6ab3fd0a6b22f078fc08aaefcfb96210ddf154e6050570",
+    "minimum_prompt_count": 3,
+    "minimum_repeats": 3,
+    "minimum_output_tokens": 32,
+    "required_device": "cpu",
+    "required_config_sha256": "00b2cce3e2f281bdf92fc5304ba5cac915a178ffccd3b9a25995ce39c00b90d3",
+    "required_signer_public_key": "zQ/qRMwF/ydazzaxEI24Xvnrl5bZxzw16JYpP0bfRuI=",
+    "required_artifact_sha256": {
+      "transformers-safetensors-reference": "e596e9d6205fdc9177569cccd7f8b471b058f66e3630c8e4326d5aad52bd18b6",
+      "llama-cpp-near-lossless-quality": "e842fdc35d7f00fda95a54e1b51731ba1d196aea45065cc9f46925fdc1d6f862",
+      "llama-cpp-quantized-performance-fit": "a88e3f570e2efeaf06b50df9859db2c70d8646aa3a2c94a14e14d5797a2921a5"
+    },
+    "required_recipe_runtime": {
+      "transformers-safetensors-reference": {
+        "runtime": "transformers-5.13.0",
+        "weight_format": "safetensors",
+        "weight_quantization": "bfloat16",
+        "device": "cpu"
+      },
+      "llama-cpp-near-lossless-quality": {
+        "runtime": "llama.cpp-9991-e920c523",
+        "weight_format": "gguf",
+        "weight_quantization": "bfloat16",
+        "device": "cpu"
+      },
+      "llama-cpp-quantized-performance-fit": {
+        "runtime": "llama.cpp-9991-e920c523",
+        "weight_format": "gguf",
+        "weight_quantization": "Q4_K_M",
+        "device": "cpu"
+      }
+    },
+    "required_backend_detail": {
+      "transformers-safetensors-reference": "torch 2.10.0+rocm7.13.0a20260513; dtype bfloat16; device cpu; intra-op threads 16",
+      "llama-cpp-near-lossless-quality": "version: 9991 (e920c523) | built with GNU 15.2.1 for Linux x86_64; binary sha256 fd8fe612970f23e447f2e717cfa51665be06b8d7315ba60556e010f6bca510dd; threads 16; parallel slots 4; ctx/slot 512; gpu layers 0",
+      "llama-cpp-quantized-performance-fit": "version: 9991 (e920c523) | built with GNU 15.2.1 for Linux x86_64; binary sha256 fd8fe612970f23e447f2e717cfa51665be06b8d7315ba60556e010f6bca510dd; threads 16; parallel slots 4; ctx/slot 512; gpu layers 0"
+    },
+    "required_host_identity": {
+      "python": "3.12.13",
+      "torch_version": "2.10.0+rocm7.13.0a20260513",
+      "transformers_version": "5.13.0",
+      "llama_server_identities": {
+        "/run/media/popov/d/DEV/llamacpp/llama.cpp/build/bin/llama-server": {
+          "sha256": "fd8fe612970f23e447f2e717cfa51665be06b8d7315ba60556e010f6bca510dd",
+          "version": "version: 9991 (e920c523) | built with GNU 15.2.1 for Linux x86_64"
+        }
+      }
+    }
+  },
+  "stop_condition": "Stop the native llama.cpp/GGUF track when, on the same machine and device as the Transformers/safetensors reference and under this plan, no performance-fit GGUF recipe delivers either a meaningful speed benefit (>=25% higher single-request decode tokens/sec without a >25% worse TTFT, or >=25% higher aggregate throughput under concurrency) or a meaningful fit benefit (>=25% lower peak resident memory), or when the near-lossless quality lane fails, which indicates a broken runtime rather than a quantization trade-off.",
+  "notes": "Quantized performance-fit output drift is reported as advisory only. It is not numerical-equivalence evidence. DGR-014 consumes this immutable v1 contract. Non-synthetic evidence must be Ed25519-signed by the pinned key and match the exact locked config, artifacts, runtimes, backends, and host runtime identity."
+}