CoolBoy/submmit
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

state: generation 5311 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-10 18:41:05 +00:00
parent e085fe5ff4
commit f8e2eca061
9 changed files with 2230 additions and 2251 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -1311,7 +1311,7 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-09-10T18:37:44.487378+00:00", "generatedAt": "2026-09-10T18:41:05.437240+00:00",
"summary": { "summary": {
"activeBlockCount": 66, "activeBlockCount": 66,
"byGpuFramework": { "byGpuFramework": {

6
.modelhub_state/architecture_history_backfill.json
View File

@@ -83,7 +83,7 @@
"8": { "8": {
"complete": false, "complete": false,
"lastError": "ModelHubAPIError: 系统错误", "lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 377, "listingErrors": 378,
"nextPage": 1, "nextPage": 1,
"recordsScanned": 0, "recordsScanned": 0,
"uniqueRecords": 0 "uniqueRecords": 0
@@ -102,12 +102,12 @@
"cutoffAt": "2026-09-04T03:55:51.365685+00:00", "cutoffAt": "2026-09-04T03:55:51.365685+00:00",
"failureLogsInspected": 0, "failureLogsInspected": 0,
"mode": "incremental_decision_only", "mode": "incremental_decision_only",
"nextAccountIndex": 8, "nextAccountIndex": 9,
"recordsScanned": 0, "recordsScanned": 0,
"seenTaskIds": [], "seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00", "startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0, "terminalRecords": 0,
"uniqueRecords": 0, "uniqueRecords": 0,
"updatedAt": "2026-09-10T18:37:44.462450+00:00", "updatedAt": "2026-09-10T18:41:05.414215+00:00",
"version": 1 "version": 1
} }

2
.modelhub_state/market_intelligence.json
View File

@@ -416,7 +416,7 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-09-10T18:35:40.538073+00:00", "generatedAt": "2026-09-10T18:38:52.916681+00:00",
"gpuStats": { "gpuStats": {
"Ascend_910-b3": { "Ascend_910-b3": {
"available": true, "available": true,

1536
.modelhub_state/official_capabilities.json
View File

File diff suppressed because it is too large Load Diff

115
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{ {
"generatedAt": "2026-09-10T17:40:38.619379+00:00", "generatedAt": "2026-09-10T18:38:45.442913+00:00",
"lastSyncTime": "2026-09-10T17:40:38.407692+00:00", "lastSyncTime": "2026-09-10T18:38:45.206121+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -1800,20 +1800,21 @@
"framework_architecture_unsupported": 47, "framework_architecture_unsupported": 47,
"memory_capacity": 1, "memory_capacity": 1,
"model_load": 24, "model_load": 24,
"platform_infrastructure": 1,
"参数/模板问题": 2, "参数/模板问题": 2,
"验证失败": 47 "验证失败": 47
}, },
"failureCount": 138, "failureCount": 139,
"failureRate": 0.9324, "failureRate": 0.9329,
"framework": "unknown", "framework": "unknown",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 1,
"successCount": 10, "successCount": 10,
"successRate": 0.0676, "successRate": 0.0671,
"targetGpu": "Iluvatar_mrv-100", "targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation", "taskType": "text-generation",
"total": 148, "total": 149,
"unresolvedFailureCount": 66 "unresolvedFailureCount": 66
}, },
"Kunlunxin_p-800|unknown|text-generation": { "Kunlunxin_p-800|unknown|text-generation": {
@@ -2301,18 +2302,19 @@
"framework_architecture_unsupported": 88, "framework_architecture_unsupported": 88,
"memory_capacity": 5, "memory_capacity": 5,
"model_load": 26, "model_load": 26,
"platform_infrastructure": 1,
"tokenizer_compatibility": 3, "tokenizer_compatibility": 3,
"参数/模板问题": 56, "参数/模板问题": 56,
"验证失败": 673 "验证失败": 673
}, },
"failureCount": 978, "failureCount": 979,
"failureRate": 0.9532, "failureRate": 0.9533,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 1,
"successCount": 48, "successCount": 48,
"successRate": 0.0468, "successRate": 0.0467,
"total": 1026, "total": 1027,
"unresolvedFailureCount": 852 "unresolvedFailureCount": 852
}, },
"vllm": { "vllm": {
@@ -2443,7 +2445,7 @@
"unresolvedFailureCount": 1 "unresolvedFailureCount": 1
} }
}, },
"generatedAt": "2026-09-10T17:40:38.613684+00:00", "generatedAt": "2026-09-10T18:38:45.436829+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 26, "attributableFailureCount": 26,
@@ -2615,17 +2617,18 @@
"framework_architecture_unsupported": 47, "framework_architecture_unsupported": 47,
"memory_capacity": 1, "memory_capacity": 1,
"model_load": 24, "model_load": 24,
"platform_infrastructure": 1,
"参数/模板问题": 2, "参数/模板问题": 2,
"验证失败": 47 "验证失败": 47
}, },
"failureCount": 138, "failureCount": 139,
"failureRate": 0.9324, "failureRate": 0.9329,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 1,
"successCount": 10, "successCount": 10,
"successRate": 0.0676, "successRate": 0.0671,
"total": 148, "total": 149,
"unresolvedFailureCount": 66 "unresolvedFailureCount": 66
}, },
"Kunlunxin_p-800": { "Kunlunxin_p-800": {
@@ -4169,11 +4172,11 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 4, "decisionTotal": 4,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 14, "ambiguous_runtime": 13,
"framework_architecture_unsupported": 4, "framework_architecture_unsupported": 4,
"参数/模板问题": 1 "参数/模板问题": 1
}, },
"failureCount": 19, "failureCount": 18,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm-mlu", "framework": "vllm-mlu",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
@@ -4185,8 +4188,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8", "targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation", "taskType": "text-generation",
"total": 19, "total": 18,
"unresolvedFailureCount": 15 "unresolvedFailureCount": 14
}, },
"Cambricon_mlu-370-x8|vllm|text-generation": { "Cambricon_mlu-370-x8|vllm|text-generation": {
"attributableFailureCount": 3, "attributableFailureCount": 3,
@@ -4267,25 +4270,26 @@
"unresolvedFailureCount": 3 "unresolvedFailureCount": 3
}, },
"Iluvatar_mrv-100|unknown|text-generation": { "Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 16, "attributableFailureCount": 15,
"consecutiveFailures": 5, "consecutiveFailures": 5,
"consecutivePlatformFailures": 0, "consecutivePlatformFailures": 1,
"decisionFailureRate": 0.8421, "decisionFailureRate": 0.8333,
"decisionSuccessRate": 0.1579, "decisionSuccessRate": 0.1667,
"decisionTotal": 19, "decisionTotal": 18,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 1, "ambiguous_runtime": 1,
"framework_architecture_unsupported": 9, "framework_architecture_unsupported": 9,
"model_load": 7 "model_load": 6,
"platform_infrastructure": 1
}, },
"failureCount": 17, "failureCount": 17,
"failureRate": 0.85, "failureRate": 0.85,
"framework": "unknown", "framework": "unknown",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": "2026-09-10T18:33:21+00:00",
"lastTerminalAt": "2026-09-10T12:40:42.405633+00:00", "lastTerminalAt": "2026-09-10T18:38:45.206121+00:00",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 1,
"successCount": 3, "successCount": 3,
"successRate": 0.15, "successRate": 0.15,
"targetGpu": "Iluvatar_mrv-100", "targetGpu": "Iluvatar_mrv-100",
@@ -4630,31 +4634,6 @@
"total": 4, "total": 4,
"unresolvedFailureCount": 4 "unresolvedFailureCount": 4
}, },
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|llama|compressed-tensors": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"lastTerminalAt": "2026-09-08T15:41:33.599000+00:00",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|nemotron_h|modelopt": { "Cambricon_mlu-370-x8|vllm-mlu|text-generation|nemotron_h|modelopt": {
"attributableFailureCount": 1, "attributableFailureCount": 1,
"consecutiveFailures": 1, "consecutiveFailures": 1,
@@ -7169,8 +7148,8 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 1615, "terminalRecords": 1616,
"totalRecords": 1702, "totalRecords": 1703,
"totals": { "totals": {
"attributableFailureCount": 421, "attributableFailureCount": 421,
"decisionFailureRate": 0.8901, "decisionFailureRate": 0.8901,
@@ -7182,37 +7161,38 @@
"framework_architecture_unsupported": 272, "framework_architecture_unsupported": 272,
"memory_capacity": 11, "memory_capacity": 11,
"model_load": 48, "model_load": 48,
"platform_infrastructure": 3, "platform_infrastructure": 4,
"repository_structure": 5, "repository_structure": 5,
"runtime_memory": 6, "runtime_memory": 6,
"tokenizer_compatibility": 39, "tokenizer_compatibility": 39,
"参数/模板问题": 98, "参数/模板问题": 98,
"验证失败": 673 "验证失败": 673
}, },
"failureCount": 1563, "failureCount": 1564,
"failureRate": 0.9678, "failureRate": 0.9678,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 3, "platformFailureCount": 4,
"successCount": 52, "successCount": 52,
"successRate": 0.0322, "successRate": 0.0322,
"total": 1615, "total": 1616,
"unresolvedFailureCount": 1139 "unresolvedFailureCount": 1139
}, },
"warnings": [ "warnings": [
"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 Vastai_va16 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 Iluvatar_mrv-100 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 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 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 MetaX_c-500 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 Iluvatar_bi-150 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 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 Iluvatar_bi-150 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 Cambricon_mlu-370-x8 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 Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。",
"组合 Iluvatar_mrv-100|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 Iluvatar_mrv-100|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-x4|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 Mthreads_s4000|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Mthreads_s4000|vllm|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|vllm|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|vllm|text-generation 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_0_17_0_corex_4_4_0|text-generation 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_0_17_0_corex_4_4_0|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -7227,11 +7207,10 @@
"组合 hygon_k100-ai|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 hygon_k100-ai|vllm|text-generation 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|text-generation 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|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Vastai_va16|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Vastai_va16|vllm|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-x4|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 hygon_k100-ai|vllm-patch-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 hygon_k100-ai|vllm-patch-tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。"
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 1702, "summarizedRecords": 1703,
"version": 1 "version": 1
} }

2
.modelhub_state/recent_outcomes.jsonl
View File

@@ -1,3 +1,4 @@
{"failReason": "platform_infrastructure", "failureAction": "open_short_gpu_framework_circuit_and_retry_other_models", "failureCategory": "platform_infrastructure", "failureClassificationReason": "platform_io_transient", "failureCode": "STORAGE_ERROR", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "gpu_framework", "framework": "", "lastSyncTime": "2026-09-10T18:38:45.206121+00:00", "modelId": "nm-testing/Qwen2-1.5B-Instruct-FP8W8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T18:33:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523310", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T17:40:38.407692+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-ACTORDER-compressed-tensors-test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T17:31:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4497059", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T17:40:38.407692+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-ACTORDER-compressed-tensors-test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T17:31:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4497059", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T17:30:55.344638+00:00", "modelId": "nm-testing/nonuniform", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T17:29:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4497068", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T17:30:55.344638+00:00", "modelId": "nm-testing/nonuniform", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T17:29:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4497068", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T17:03:45.496007+00:00", "modelId": "RedHatAI/starcoder2-3b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T17:01:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4497067", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T17:03:45.496007+00:00", "modelId": "RedHatAI/starcoder2-3b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T17:01:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4497067", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-mlu", "lastSyncTime": "2026-09-10T15:27:09.820580+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14293335560, "estimatedRequiredGiB": 15.977, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 14295942065, "modelscopeLicense": "mit", "modelscopeParams": 13960238080, "modelscopeTags": ["license:mit", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14295942065}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T06:46:06.810137+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712809", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-mlu", "lastSyncTime": "2026-09-10T15:27:09.820580+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14293335560, "estimatedRequiredGiB": 15.977, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 14295942065, "modelscopeLicense": "mit", "modelscopeParams": 13960238080, "modelscopeTags": ["license:mit", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14295942065}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T06:46:06.810137+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712809", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-mlu", "lastSyncTime": "2026-09-10T13:14:20.004644+00:00", "modelId": "RedHatAI/starcoder2-3b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3484485728, "estimatedRequiredGiB": 3.898, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 3487786133, "modelscopeLicense": "other", "modelscopeParams": 3181366272, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3487786133}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T06:46:06.808048+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712807", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-mlu", "lastSyncTime": "2026-09-10T13:14:20.004644+00:00", "modelId": "RedHatAI/starcoder2-3b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3484485728, "estimatedRequiredGiB": 3.898, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 3487786133, "modelscopeLicense": "other", "modelscopeParams": 3181366272, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3487786133}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T06:46:06.808048+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712807", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-mlu", "lastSyncTime": "2026-09-08T20:58:55.412656+00:00", "modelId": "RedHatAI/Qwen2.5-1.5B-quantized.w4a16", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1611497856, "estimatedRequiredGiB": 1.819, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 1627385309, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1781159424, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:chat", "custom_tag:neuralmagic", "custom_tag:llmcompressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 1627385309}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T06:46:06.804740+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712806", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-mlu", "lastSyncTime": "2026-09-08T20:58:55.412656+00:00", "modelId": "RedHatAI/Qwen2.5-1.5B-quantized.w4a16", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1611497856, "estimatedRequiredGiB": 1.819, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 1627385309, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1781159424, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:chat", "custom_tag:neuralmagic", "custom_tag:llmcompressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 1627385309}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T06:46:06.804740+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712806", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-mlu", "lastSyncTime": "2026-09-08T15:41:33.599000+00:00", "modelId": "neuralmagic/Llama-3.2-1B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2023929984, "estimatedRequiredGiB": 2.272, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2033083373, "modelscopeLicense": "llama3.2", "modelscopeParams": 1498482688, "modelscopeTags": ["license:llama3.2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama", "custom_tag:llama-3", "custom_tag:neuralmagic", "custom_tag:llmcompressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2033083377}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T06:46:06.795745+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712800", "taskType": "text-generation", "verifyResult": -1}

1624
.modelhub_state/recovery_active_tasks.jsonl
View File

File diff suppressed because it is too large Load Diff

1174
.modelhub_state/recovery_intents.jsonl
View File

File diff suppressed because it is too large Load Diff

20
manifest.json
View File

@@ -1,24 +1,24 @@
{ {
"agentVersion": "2026.09.04.4", "agentVersion": "2026.09.04.4",
"checksums": { "checksums": {
".modelhub_state/architecture_compatibility_blacklist.json": "cf8ee94b0dde353ba62f084188f12db126cec296fe08b4ef9eb3043695bad04f", ".modelhub_state/architecture_compatibility_blacklist.json": "289469d617e4b9a25567c75bbad14956eed292984c76693344f979b27b002b0d",
".modelhub_state/architecture_history_backfill.json": "6b4c07603bbb7b8039350c647b4f3557afad82e609c6b4ebb4437c5d45f73dc0", ".modelhub_state/architecture_history_backfill.json": "ca16b77c486502f4afd12dd35b08e25266d71a21b556a2e034a89f4777cc295e",
".modelhub_state/market_intelligence.json": "c64e3a472d3e612285ded56629528288ec57d5149146a6777984f60734d4c2ea", ".modelhub_state/market_intelligence.json": "bb91b498e331af268f6f34f387ce8188789c2938c5635cb6cdaf71f3d6d6d5ee",
".modelhub_state/official_capabilities.json": "f77e5e34d81c6f06bc2aef30b94a83f283387cf438d1dc3f061a0765ea728eba", ".modelhub_state/official_capabilities.json": "79dac2526cb317025a2007d1a3b0eb1953fcd832edfca122a83f2d37acf6e8e9",
".modelhub_state/outcome_checkpoint.json": "77b2e5ed39f7618cbecd4318aa3a25feffbbd478861578b9314cd74b7543d467", ".modelhub_state/outcome_checkpoint.json": "0b19b5a0925306abb4939b2b7ff68cb27fa330b35037846fb13d35ee375dc597",
".modelhub_state/queue_cleanup_latest.json": "c4c0c2f745124fbabf68b2aa082c5aeee0f45dbb41d40369e8064e674a33adbe", ".modelhub_state/queue_cleanup_latest.json": "c4c0c2f745124fbabf68b2aa082c5aeee0f45dbb41d40369e8064e674a33adbe",
".modelhub_state/recent_outcomes.jsonl": "1463b2ee90f780dc87c10be9c149f785d258f8f3440492fcdfcf44f2c43f78ab", ".modelhub_state/recent_outcomes.jsonl": "64db2bc892f7a375d9286ffc29dd889007169aba4b3496277c095eface4e3de1",
".modelhub_state/recovery_active_tasks.jsonl": "f778114aa15f449cc51741f5ba1312e00884f6245918b06c3f5acfe80e6cdeaa", ".modelhub_state/recovery_active_tasks.jsonl": "1e526c1483ba3e2fcb5a90b07120067c4b1173a42b0caa9422acae0b6d364ad6",
".modelhub_state/recovery_intents.jsonl": "56a5899c049e4d04c8d4360956b4cbe2050b8f0d24b608d1534ecad2d9fe223f", ".modelhub_state/recovery_intents.jsonl": "aa3f5be5c6d9e9af693c3847bc6b895b796d461c94c44fdb58c577275a7204a3",
".modelhub_state/routing_intelligence.json": "7e77ebd4538eae240305b9b7218df18db6f864488fe914a9ce22b09526e6df6c", ".modelhub_state/routing_intelligence.json": "7e77ebd4538eae240305b9b7218df18db6f864488fe914a9ce22b09526e6df6c",
".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03", ".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03",
".modelhub_state/worker_crashes.jsonl": "7fa483580e87374493226e80bcf40bf8044847acba70045c96fa175966a1a8ba", ".modelhub_state/worker_crashes.jsonl": "7fa483580e87374493226e80bcf40bf8044847acba70045c96fa175966a1a8ba",
"ledger/submissions.jsonl": "666d3d2a6579643ce987f9dc944f3169c02e619fe50a5b6144105e85857aa8c5", "ledger/submissions.jsonl": "666d3d2a6579643ce987f9dc944f3169c02e619fe50a5b6144105e85857aa8c5",
"outcomes/submissions.jsonl": "9f391d44d672b11802eca45cb34e76daf4d6f37684b09a9ee06fbb60c10bb664" "outcomes/submissions.jsonl": "9f391d44d672b11802eca45cb34e76daf4d6f37684b09a9ee06fbb60c10bb664"
}, },
"generation": 5310, "generation": 5311,
"phase": "cycle", "phase": "cycle",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-09-10T18:37:44.578719+00:00", "updatedAt": "2026-09-10T18:41:05.966559+00:00",
"writerId": "18252d8a8ef94333abd55823b2d81c42" "writerId": "18252d8a8ef94333abd55823b2d81c42"
} }