Files
neuron-tai/.scratch/distributed-gguf-runtime/evidence/DGR-017/resource-plan.json

256 lines
8.0 KiB
JSON

{
"generated_by": "DGR-017 meshnet_node.glm_alpha.planner",
"target": {
"gguf_repo_id": "unsloth/GLM-5.2-GGUF",
"gguf_revision": "abc55e72527792c6e77069c99b4cb7de16fa9f23",
"quantization": "UD-IQ1_S",
"total_bytes": 216715360960,
"total_gib": 201.832,
"total_gb": 216.715
},
"manifest_sha256": "0b6aed04479d204902bb64c0203f1a46cab26a47b378ecccf85237b63f6c1962",
"architecture_snapshot_sha256": "253fbd94b06b42acc4724ec2c7f33914e2d4cc43f54a36dff6af19a80ae6ceb1",
"alpha_contract_sha256": "aab23220280c053a3c14ff559df3cb5c9e1bf7f0f7188c6519e2e9d9ad036ed9",
"kv_assumptions": {
"dtype": "Q8_0",
"bytes_per_value": 1.0625,
"context_tokens": 16384,
"concurrency": 1,
"indexer_layout": "conservative",
"mla_values_per_token_per_layer": 576,
"backbone_layers": 78,
"indexer_full_layers": 21,
"note": "Alpha budgets indexer keys across all 78 layers (current experimental DSA layout), not only the 21 Full layers."
},
"kv_table_gib": {
"16384": {
"mla_only_q8_gib": 0.73,
"optimized_dsa_q8_gib": 0.77,
"conservative_dsa_q8_gib": 0.89,
"conservative_dsa_f16_gib": 1.68
},
"131072": {
"mla_only_q8_gib": 5.83,
"optimized_dsa_q8_gib": 6.18,
"conservative_dsa_q8_gib": 7.12,
"conservative_dsa_f16_gib": 13.41
},
"1048576": {
"mla_only_q8_gib": 46.62,
"optimized_dsa_q8_gib": 49.41,
"conservative_dsa_q8_gib": 56.98,
"conservative_dsa_f16_gib": 107.25
}
},
"aggregate_hard_fit_floor_gib": 224.0,
"aggregate_floor_class": "experimental_hard_fit_floor",
"placement_imbalance_factor": 1.1,
"tier_table": {
"32": {
"physical_usable_gib": 32.0,
"reserve_gib": 8.0,
"placement_budget_gib": 24.0,
"weight_gib": 201.832,
"kv_gib": 0.89,
"total_placement_gib": 202.722,
"arithmetic_minimum_nodes": 9,
"recommended_nodes": 10,
"imbalance_factor": 1.1
},
"48": {
"physical_usable_gib": 48.0,
"reserve_gib": 9.6,
"placement_budget_gib": 38.4,
"weight_gib": 201.832,
"kv_gib": 0.89,
"total_placement_gib": 202.722,
"arithmetic_minimum_nodes": 6,
"recommended_nodes": 6,
"imbalance_factor": 1.1
},
"64": {
"physical_usable_gib": 64.0,
"reserve_gib": 12.8,
"placement_budget_gib": 51.2,
"weight_gib": 201.832,
"kv_gib": 0.89,
"total_placement_gib": 202.722,
"arithmetic_minimum_nodes": 4,
"recommended_nodes": 5,
"imbalance_factor": 1.1
},
"96": {
"physical_usable_gib": 96.0,
"reserve_gib": 19.2,
"placement_budget_gib": 76.8,
"weight_gib": 201.832,
"kv_gib": 0.89,
"total_placement_gib": 202.722,
"arithmetic_minimum_nodes": 3,
"recommended_nodes": 3,
"imbalance_factor": 1.1
},
"128": {
"physical_usable_gib": 128.0,
"reserve_gib": 25.6,
"placement_budget_gib": 102.4,
"weight_gib": 201.832,
"kv_gib": 0.89,
"total_placement_gib": 202.722,
"arithmetic_minimum_nodes": 2,
"recommended_nodes": 3,
"imbalance_factor": 1.1
}
},
"routes": {
"recommended_5x64_unified": {
"node_count": 5,
"aggregate_usable_gib": 320.0,
"aggregate_placement_budget_gib": 256.0,
"required_placement_gib": 202.722,
"fits": true,
"meets_hard_fit_floor": true,
"no_single_node_can_admit_target": true,
"headroom_gib": 53.278,
"reasons": []
},
"recommended_3x96_unified": {
"node_count": 3,
"aggregate_usable_gib": 288.0,
"aggregate_placement_budget_gib": 230.4,
"required_placement_gib": 202.722,
"fits": true,
"meets_hard_fit_floor": true,
"no_single_node_can_admit_target": true,
"headroom_gib": 27.678,
"reasons": []
},
"recommended_3x128_unified": {
"node_count": 3,
"aggregate_usable_gib": 384.0,
"aggregate_placement_budget_gib": 307.2,
"required_placement_gib": 202.722,
"fits": true,
"meets_hard_fit_floor": true,
"no_single_node_can_admit_target": true,
"headroom_gib": 104.478,
"reasons": []
},
"fit_probe_2x128_unified": {
"node_count": 2,
"aggregate_usable_gib": 256.0,
"aggregate_placement_budget_gib": 204.8,
"required_placement_gib": 202.722,
"fits": true,
"meets_hard_fit_floor": true,
"no_single_node_can_admit_target": true,
"headroom_gib": 2.078,
"reasons": []
},
"fit_probe_4x64_unified": {
"node_count": 4,
"aggregate_usable_gib": 256.0,
"aggregate_placement_budget_gib": 204.8,
"required_placement_gib": 202.722,
"fits": true,
"meets_hard_fit_floor": true,
"no_single_node_can_admit_target": true,
"headroom_gib": 2.078,
"reasons": []
},
"hard_fit_floor_2x112_unified": {
"node_count": 2,
"aggregate_usable_gib": 224.0,
"aggregate_placement_budget_gib": 179.2,
"required_placement_gib": 202.722,
"fits": false,
"meets_hard_fit_floor": true,
"no_single_node_can_admit_target": true,
"headroom_gib": -23.522,
"reasons": [
"aggregate placement budget 179.2 GiB is below the 202.7 GiB the target needs after each node's reserve"
]
},
"insufficient_3x64_unified": {
"node_count": 3,
"aggregate_usable_gib": 192.0,
"aggregate_placement_budget_gib": 153.6,
"required_placement_gib": 202.722,
"fits": false,
"meets_hard_fit_floor": false,
"no_single_node_can_admit_target": true,
"headroom_gib": -49.122,
"reasons": [
"aggregate placement budget 153.6 GiB is below the 202.7 GiB the target needs after each node's reserve",
"aggregate usable memory 192.0 GiB is below the 224 GiB experimental hard-fit floor"
]
}
},
"seams": {
"3_nodes_2.5gbe": {
"node_count": 3,
"seam_count": 2,
"hidden_size": 6144,
"bytes_per_token_per_seam": 12288,
"prefill_bytes_per_seam": 201326592,
"decode_bytes_per_seam_per_token": 12288,
"dsa_sideband_bytes_per_query": 8192,
"link_rate_gbps": 2.5,
"meets_alpha_minimum": true,
"is_recommended_link": false,
"decode_serialization_ms_per_token": 0.0786,
"decode_latency_ms_per_token": 1.0,
"decode_bandwidth_share_ms_per_token": 0.0786,
"prefill_serialization_ms": 1288.49
},
"3_nodes_10.0gbe": {
"node_count": 3,
"seam_count": 2,
"hidden_size": 6144,
"bytes_per_token_per_seam": 12288,
"prefill_bytes_per_seam": 201326592,
"decode_bytes_per_seam_per_token": 12288,
"dsa_sideband_bytes_per_query": 8192,
"link_rate_gbps": 10.0,
"meets_alpha_minimum": true,
"is_recommended_link": true,
"decode_serialization_ms_per_token": 0.0197,
"decode_latency_ms_per_token": 1.0,
"decode_bandwidth_share_ms_per_token": 0.0197,
"prefill_serialization_ms": 322.123
},
"5_nodes_2.5gbe": {
"node_count": 5,
"seam_count": 4,
"hidden_size": 6144,
"bytes_per_token_per_seam": 12288,
"prefill_bytes_per_seam": 201326592,
"decode_bytes_per_seam_per_token": 12288,
"dsa_sideband_bytes_per_query": 8192,
"link_rate_gbps": 2.5,
"meets_alpha_minimum": true,
"is_recommended_link": false,
"decode_serialization_ms_per_token": 0.1573,
"decode_latency_ms_per_token": 2.0,
"decode_bandwidth_share_ms_per_token": 0.1573,
"prefill_serialization_ms": 2576.98
},
"5_nodes_10.0gbe": {
"node_count": 5,
"seam_count": 4,
"hidden_size": 6144,
"bytes_per_token_per_seam": 12288,
"prefill_bytes_per_seam": 201326592,
"decode_bytes_per_seam_per_token": 12288,
"dsa_sideband_bytes_per_query": 8192,
"link_rate_gbps": 10.0,
"meets_alpha_minimum": true,
"is_recommended_link": true,
"decode_serialization_ms_per_token": 0.0393,
"decode_latency_ms_per_token": 2.0,
"decode_bandwidth_share_ms_per_token": 0.0393,
"prefill_serialization_ms": 644.245
}
}
}