966aa10854
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
170 lines
6.5 KiB
JSON
170 lines
6.5 KiB
JSON
{
|
|
"artifact_sha256": {
|
|
"llama-cpp-near-lossless-quality": "e842fdc35d7f00fda95a54e1b51731ba1d196aea45065cc9f46925fdc1d6f862",
|
|
"llama-cpp-quantized-performance-fit": "a88e3f570e2efeaf06b50df9859db2c70d8646aa3a2c94a14e14d5797a2921a5",
|
|
"transformers-safetensors-reference": "e596e9d6205fdc9177569cccd7f8b471b058f66e3630c8e4326d5aad52bd18b6"
|
|
},
|
|
"backend_detail": {
|
|
"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",
|
|
"transformers-safetensors-reference": "torch 2.10.0+rocm7.13.0a20260513; dtype bfloat16; device cpu; intra-op threads 16"
|
|
},
|
|
"evidence_class": "local-real",
|
|
"host": {
|
|
"accelerator_name": "Radeon 8060S Graphics",
|
|
"accelerator_runtime": "7.13.26183",
|
|
"benchmark_lane": "cpu-controlled-baseline",
|
|
"converter_sha256": "c819f18fb22927b49fabc3b35d1c9e21ee638b3817eccd1bd4efbcc7116eeb4d",
|
|
"cpu_count": 32,
|
|
"cuda_available": true,
|
|
"hostname": "fedora",
|
|
"llama_cpp_commit": "e920c523e3b8a0163fe498af5bf90df35ff51d25",
|
|
"llama_cpp_version": "9991",
|
|
"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"
|
|
}
|
|
},
|
|
"llama_server_sha256": "fd8fe612970f23e447f2e717cfa51665be06b8d7315ba60556e010f6bca510dd",
|
|
"platform": "Linux-7.0.14-101.fc43.x86_64-x86_64-with-glibc2.42",
|
|
"python": "3.12.13",
|
|
"quantizer_sha256": "bd0cc8c7be6d48aad4755b31062e0e59a887cbadd43dbb8771853d5858bb198f",
|
|
"torch_version": "2.10.0+rocm7.13.0a20260513",
|
|
"transformers_version": "5.13.0"
|
|
},
|
|
"model_id": "Qwen/Qwen2.5-0.5B-Instruct",
|
|
"model_revision": "7ae557604adf67be50417f59c2c2f167def9a775",
|
|
"plan_sha256": "efe24690a9a7164bac6ab3fd0a6b22f078fc08aaefcfb96210ddf154e6050570",
|
|
"provenance": {
|
|
"completed_at": "2026-07-22T05:52:30.445799Z",
|
|
"config_sha256": "00b2cce3e2f281bdf92fc5304ba5cac915a178ffccd3b9a25995ce39c00b90d3",
|
|
"producer": "meshnet_node.recipe_drivers.run_configured_benchmark/v1",
|
|
"run_id": "59b12968-c5d0-4391-90f4-0cd2aff77b21",
|
|
"schema_version": 1,
|
|
"signature": "aExtG1Y0fWFaqlKEtUOOpXZrganVAxbLvpov2WVgm19eNJ50VheeI7CuRhlWx4SJX9OFto2WuLaVPhjwSA88Cw==",
|
|
"signature_algorithm": "ed25519",
|
|
"signer_public_key_sha256": "8baca8742d9b3ed0c3fc54929c23f75ec8c1c739900aaf5334780d598ffa84de",
|
|
"started_at": "2026-07-22T05:51:36.511891Z"
|
|
},
|
|
"recipe_runtime": {
|
|
"llama-cpp-near-lossless-quality": {
|
|
"device": "cpu",
|
|
"runtime": "llama.cpp-9991-e920c523",
|
|
"weight_format": "gguf",
|
|
"weight_quantization": "bfloat16"
|
|
},
|
|
"llama-cpp-quantized-performance-fit": {
|
|
"device": "cpu",
|
|
"runtime": "llama.cpp-9991-e920c523",
|
|
"weight_format": "gguf",
|
|
"weight_quantization": "Q4_K_M"
|
|
},
|
|
"transformers-safetensors-reference": {
|
|
"device": "cpu",
|
|
"runtime": "transformers-5.13.0",
|
|
"weight_format": "safetensors",
|
|
"weight_quantization": "bfloat16"
|
|
}
|
|
},
|
|
"recipes": {
|
|
"llama-cpp-near-lossless-quality": {
|
|
"artifact_bytes": 994156448,
|
|
"available": true,
|
|
"concurrency": {
|
|
"1": {
|
|
"aggregate_decode_tokens_per_sec": 89.2873,
|
|
"decode_tokens_per_sec": 102.5344,
|
|
"failures": 0,
|
|
"latency_p50_ms": 316.647,
|
|
"latency_p95_ms": 374.8515,
|
|
"peak_rss_bytes": 1110106112,
|
|
"peak_vram_bytes": 0,
|
|
"prefill_tokens_per_sec": 1740.0213,
|
|
"ttft_p50_ms": 15.067,
|
|
"ttft_p95_ms": 65.191
|
|
},
|
|
"4": {
|
|
"aggregate_decode_tokens_per_sec": 218.1128,
|
|
"decode_tokens_per_sec": 80.0623,
|
|
"failures": 0,
|
|
"latency_p50_ms": 403.9781,
|
|
"latency_p95_ms": 767.6557,
|
|
"peak_rss_bytes": 1139265536,
|
|
"peak_vram_bytes": 0,
|
|
"prefill_tokens_per_sec": 1064.6179,
|
|
"ttft_p50_ms": 36.611,
|
|
"ttft_p95_ms": 178.801
|
|
}
|
|
},
|
|
"device": "cpu",
|
|
"lane": "quality"
|
|
},
|
|
"llama-cpp-quantized-performance-fit": {
|
|
"artifact_bytes": 397807520,
|
|
"available": true,
|
|
"concurrency": {
|
|
"1": {
|
|
"aggregate_decode_tokens_per_sec": 149.8675,
|
|
"decode_tokens_per_sec": 213.1452,
|
|
"failures": 0,
|
|
"latency_p50_ms": 161.7164,
|
|
"latency_p95_ms": 282.5491,
|
|
"peak_rss_bytes": 541663232,
|
|
"peak_vram_bytes": 0,
|
|
"prefill_tokens_per_sec": 1181.0842,
|
|
"ttft_p50_ms": 17.252,
|
|
"ttft_p95_ms": 130.529
|
|
},
|
|
"4": {
|
|
"aggregate_decode_tokens_per_sec": 235.6963,
|
|
"decode_tokens_per_sec": 94.7604,
|
|
"failures": 0,
|
|
"latency_p50_ms": 373.7211,
|
|
"latency_p95_ms": 759.3151,
|
|
"peak_rss_bytes": 571027456,
|
|
"peak_vram_bytes": 0,
|
|
"prefill_tokens_per_sec": 567.7335,
|
|
"ttft_p50_ms": 42.086,
|
|
"ttft_p95_ms": 312.645
|
|
}
|
|
},
|
|
"device": "cpu",
|
|
"lane": "performance-fit"
|
|
},
|
|
"transformers-safetensors-reference": {
|
|
"artifact_bytes": 999586347,
|
|
"available": true,
|
|
"concurrency": {
|
|
"1": {
|
|
"aggregate_decode_tokens_per_sec": 44.4625,
|
|
"decode_tokens_per_sec": 50.8327,
|
|
"failures": 0,
|
|
"latency_p50_ms": 701.9146,
|
|
"latency_p95_ms": 776.2706,
|
|
"peak_rss_bytes": 1933221888,
|
|
"peak_vram_bytes": 0,
|
|
"prefill_tokens_per_sec": 699.7553,
|
|
"ttft_p50_ms": 32.8569,
|
|
"ttft_p95_ms": 173.7161
|
|
},
|
|
"4": {
|
|
"aggregate_decode_tokens_per_sec": 48.849,
|
|
"decode_tokens_per_sec": 13.4779,
|
|
"failures": 0,
|
|
"latency_p50_ms": 2503.1601,
|
|
"latency_p95_ms": 2600.6307,
|
|
"peak_rss_bytes": 2170908672,
|
|
"peak_vram_bytes": 0,
|
|
"prefill_tokens_per_sec": 264.5822,
|
|
"ttft_p50_ms": 95.7502,
|
|
"ttft_p95_ms": 425.4973
|
|
}
|
|
},
|
|
"device": "cpu",
|
|
"lane": "quality"
|
|
}
|
|
},
|
|
"reference_recipe_id": "transformers-safetensors-reference"
|
|
}
|