state: generation 11846 (cycle_no_slots)

This commit is contained in:
2026-09-21 22:40:02 +00:00
parent 4d9e1a1405
commit 367ea0c50e
5 changed files with 1809 additions and 1809 deletions

View File

@@ -2869,7 +2869,7 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-09-21T22:37:57.057699+00:00", "generatedAt": "2026-09-21T22:39:51.306112+00:00",
"summary": { "summary": {
"activeBlockCount": 144, "activeBlockCount": 144,
"byGpuFramework": { "byGpuFramework": {

View File

@@ -1,6 +1,6 @@
{ {
"generatedAt": "2026-09-21T22:36:34.275044+00:00", "generatedAt": "2026-09-21T22:39:51.232955+00:00",
"lastSyncTime": "2026-09-21T22:36:33.961892+00:00", "lastSyncTime": "2026-09-21T22:39:51.153783+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -5357,9 +5357,9 @@
"model_load": 4, "model_load": 4,
"repository_structure": 2, "repository_structure": 2,
"runtime_memory": 9, "runtime_memory": 9,
"参数/模板问题": 8 "参数/模板问题": 11
}, },
"failureCount": 55, "failureCount": 58,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm-patch-tokenizer", "framework": "vllm-patch-tokenizer",
"pendingCount": 0, "pendingCount": 0,
@@ -5369,8 +5369,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "hygon_k100-ai", "targetGpu": "hygon_k100-ai",
"taskType": "text-generation", "taskType": "text-generation",
"total": 55, "total": 58,
"unresolvedFailureCount": 24 "unresolvedFailureCount": 27
}, },
"hygon_k100-ai|vllm|text-generation": { "hygon_k100-ai|vllm|text-generation": {
"attributableFailureCount": 658, "attributableFailureCount": 658,
@@ -5609,17 +5609,17 @@
"model_load": 4, "model_load": 4,
"repository_structure": 2, "repository_structure": 2,
"runtime_memory": 9, "runtime_memory": 9,
"参数/模板问题": 8 "参数/模板问题": 11
}, },
"failureCount": 55, "failureCount": 58,
"failureRate": 1.0, "failureRate": 1.0,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 0, "successCount": 0,
"successRate": 0.0, "successRate": 0.0,
"total": 55, "total": 58,
"unresolvedFailureCount": 24 "unresolvedFailureCount": 27
}, },
"vllm_0_17_0_corex_4_4_0": { "vllm_0_17_0_corex_4_4_0": {
"attributableFailureCount": 39, "attributableFailureCount": 39,
@@ -5698,7 +5698,7 @@
"unresolvedFailureCount": 120 "unresolvedFailureCount": 120
} }
}, },
"generatedAt": "2026-09-21T22:36:34.263803+00:00", "generatedAt": "2026-09-21T22:39:51.220187+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 99, "attributableFailureCount": 99,
@@ -6099,19 +6099,19 @@
"repository_structure": 118, "repository_structure": 118,
"runtime_memory": 62, "runtime_memory": 62,
"tokenizer_compatibility": 79, "tokenizer_compatibility": 79,
"参数/模板问题": 388, "参数/模板问题": 391,
"日志缺失": 66, "日志缺失": 66,
"验证失败": 27 "验证失败": 27
}, },
"failureCount": 1497, "failureCount": 1500,
"failureRate": 0.9791, "failureRate": 0.9791,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 4, "platformFailureCount": 4,
"successCount": 32, "successCount": 32,
"successRate": 0.0209, "successRate": 0.0209,
"total": 1529, "total": 1532,
"unresolvedFailureCount": 789 "unresolvedFailureCount": 792
} }
}, },
"observedGpuMemoryGiB": { "observedGpuMemoryGiB": {
@@ -38480,8 +38480,8 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 16433, "terminalRecords": 16436,
"totalRecords": 16627, "totalRecords": 16630,
"totals": { "totals": {
"attributableFailureCount": 5923, "attributableFailureCount": 5923,
"decisionFailureRate": 0.8619, "decisionFailureRate": 0.8619,
@@ -38500,35 +38500,35 @@
"repository_structure": 739, "repository_structure": 739,
"runtime_memory": 85, "runtime_memory": 85,
"tokenizer_compatibility": 667, "tokenizer_compatibility": 667,
"参数/模板问题": 3192, "参数/模板问题": 3195,
"日志缺失": 719, "日志缺失": 719,
"验证失败": 674 "验证失败": 674
}, },
"failureCount": 15484, "failureCount": 15487,
"failureRate": 0.9423, "failureRate": 0.9423,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 925, "platformFailureCount": 925,
"successCount": 949, "successCount": 949,
"successRate": 0.0577, "successRate": 0.0577,
"total": 16433, "total": 16436,
"unresolvedFailureCount": 8636 "unresolvedFailureCount": 8639
}, },
"warnings": [ "warnings": [
"GPU Iluvatar_mrv-100 本地统计失败率偏高(≥50%),建议重点关注。", "GPU Iluvatar_mrv-100 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Mthreads_s4000 本地统计失败率偏高(≥50%),建议重点关注。", "GPU Mthreads_s4000 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Kunlunxin_p-800 本地统计失败率偏高(≥50%),建议重点关注。", "GPU Kunlunxin_p-800 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU MetaX_c-500 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Biren_166m 本地统计失败率偏高(≥50%),建议重点关注。", "GPU Biren_166m 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Iluvatar_bi-100 本地统计失败率偏高(≥50%),建议重点关注。", "GPU Iluvatar_bi-100 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Sunrise_pt-200-x1 本地统计失败率偏高(≥50%),建议重点关注。", "GPU Sunrise_pt-200-x1 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Ascend_910-b3 本地统计失败率偏高(≥50%),建议重点关注。", "GPU Ascend_910-b3 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Vastai_va16 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高(≥50%),建议重点关注。", "GPU Cambricon_mlu-370-x4 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Iluvatar_bi-150 本地统计失败率偏高(≥50%),建议重点关注。", "GPU Iluvatar_bi-150 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU hygon_k100-ai 本地统计失败率偏高(≥50%),建议重点关注。", "GPU hygon_k100-ai 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Ascend_910-b4 本地统计失败率偏高(≥50%),建议重点关注。", "GPU Ascend_910-b4 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Vastai_va16 本地统计失败率偏高(≥50%),建议重点关注。", "GPU MetaX_c-500 本地统计失败率偏高(≥50%),建议重点关注。",
"组合 Iluvatar_bi-150|vllm|visual-multi-modal 近期失败集中,建议降低该 GPU+框架的提交优先级。", "组合 Iluvatar_bi-150|vllm|visual-multi-modal 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。", "组合 Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Cambricon_mlu-370-x8|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。", "组合 Cambricon_mlu-370-x8|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -38568,6 +38568,6 @@
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 16627, "summarizedRecords": 16630,
"version": 1 "version": 1
} }

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@@ -2,24 +2,24 @@
"agentVersion": "2026.09.20.2", "agentVersion": "2026.09.20.2",
"checksums": { "checksums": {
".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1", ".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1",
".modelhub_state/architecture_compatibility_blacklist.json": "2e021b6ec0e35b8b9b448059caf592726f6e23c3630b6a7698c11ddf4c103166", ".modelhub_state/architecture_compatibility_blacklist.json": "543c700f05686b02c4149baa6aa6175449b16ac9cc09d7b9c92a3de49721a3bc",
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
".modelhub_state/market_intelligence.json": "768b0cb32e9a5d4e673454f5d49a38c4d6062fe904ddbd90897f97082fd53f93", ".modelhub_state/market_intelligence.json": "768b0cb32e9a5d4e673454f5d49a38c4d6062fe904ddbd90897f97082fd53f93",
".modelhub_state/official_capabilities.json": "6951bae6b21792416272616ab50a0af50eb9ec04959a94eacde62688ae1f4b2d", ".modelhub_state/official_capabilities.json": "6951bae6b21792416272616ab50a0af50eb9ec04959a94eacde62688ae1f4b2d",
".modelhub_state/outcome_checkpoint.json": "43504ac6d2d40746da125259c28b0344713cbd7cb0a41d3d8d6cc579e4d6e88d", ".modelhub_state/outcome_checkpoint.json": "78dc0bb0b790b07493f074e5eee18c8684149e04dfb3cea125db06e9c012f701",
".modelhub_state/queue_cleanup_latest.json": "b1b7282c6b358c385382f40f1d98c1271162d249ef523e283e95261951a8cd2b", ".modelhub_state/queue_cleanup_latest.json": "b1b7282c6b358c385382f40f1d98c1271162d249ef523e283e95261951a8cd2b",
".modelhub_state/recent_outcomes.jsonl": "d532366bd98a9a0563ee0a2b0282e238acc915f6b665670ee87caa0a49abae61", ".modelhub_state/recent_outcomes.jsonl": "d532366bd98a9a0563ee0a2b0282e238acc915f6b665670ee87caa0a49abae61",
".modelhub_state/recovery_active_tasks.jsonl": "c15e8719ff8b3f895e0ca55c208230ddf2fef6bf8a393357169d41dad45d4ae9", ".modelhub_state/recovery_active_tasks.jsonl": "4c1b2d3dca4a3b41eef1fb6952cefceab894fa671b987a6b3b8ea5f35fe65593",
".modelhub_state/recovery_intents.jsonl": "7a513eafb0ebbb8c7176dde25699f743fee6e8d287f63b16f7800f6d5be18c6e", ".modelhub_state/recovery_intents.jsonl": "8b5011e2e847651ee361f7e5c8b792d6eae85beef92eb73e65e64c179950034d",
".modelhub_state/routing_intelligence.json": "2a99f77edacef8224108ed91b32905d5da6679b5c995c13018c376b5f2f09c88", ".modelhub_state/routing_intelligence.json": "2a99f77edacef8224108ed91b32905d5da6679b5c995c13018c376b5f2f09c88",
".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989", ".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989",
".modelhub_state/worker_crashes.jsonl": "07505b69e0b050da5f90f8b046a3069d3e1ca2574ca39896bc7d8a66293167f7", ".modelhub_state/worker_crashes.jsonl": "07505b69e0b050da5f90f8b046a3069d3e1ca2574ca39896bc7d8a66293167f7",
"ledger/submissions.jsonl": "b1506e5166e1a691fdd6cfe5bbf1e07807cc8daa2b26580fe3d08c2a05a85642", "ledger/submissions.jsonl": "b1506e5166e1a691fdd6cfe5bbf1e07807cc8daa2b26580fe3d08c2a05a85642",
"outcomes/submissions.jsonl": "3f3cbca8de4535ca56bee1fbe4667d4fc90455995a205b3448ca6e3bb1496b90" "outcomes/submissions.jsonl": "3f3cbca8de4535ca56bee1fbe4667d4fc90455995a205b3448ca6e3bb1496b90"
}, },
"generation": 11845, "generation": 11846,
"phase": "cycle", "phase": "cycle_no_slots",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-09-21T22:39:00.248644+00:00", "updatedAt": "2026-09-21T22:40:02.088455+00:00",
"writerId": "8b35139af6674067a339a670222d4b67" "writerId": "8b35139af6674067a339a670222d4b67"
} }