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

state: generation 21613 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-10-07 00:17:43 +00:00
parent fe0697b2a9
commit 1c85b9693d
10 changed files with 1969 additions and 1945 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -2297,17 +2297,19 @@
"mthreads_s4000|vllm|text-generation|model_type:qwen3_5_text": {
"architectureSignature": "model_type:qwen3_5_text",
"architectures": [],
"evidenceCount": 1,
"expiresAt": "2026-11-05T08:52:27.648162+00:00",
"evidenceCount": 2,
"expiresAt": "2026-11-05T08:52:27.660895+00:00",
"framework": "vllm",
"latestFailureAt": "2026-10-06T08:52:27.648162+00:00",
"latestFailureAt": "2026-10-06T08:52:27.660895+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "qwen3_5_text",
"sourceModelIds": [
"TokenRhythm/NeoHorse-1-4B",
"TokenRhythm/NeoHorse-1-9B"
],
"sourceTaskIds": [
"5320023",
"5320021"
],
"targetGpu": "Mthreads_s4000",
@@ -2777,7 +2779,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-10-07T00:04:31.237797+00:00",
"generatedAt": "2026-10-07T00:15:57.230285+00:00",
"summary": {
"activeBlockCount": 140,
"byGpuFramework": {

2
.modelhub_state/market_intelligence.json
View File

@@ -434,7 +434,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-10-07T00:14:54.056869+00:00",
"generatedAt": "2026-10-07T00:17:34.467406+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,

22
.modelhub_state/official_capabilities.json
View File

@@ -1,5 +1,5 @@
{
"catalogUpdatedAt": "2026-10-07T00:14:54.056869+00:00",
"catalogUpdatedAt": "2026-10-07T00:17:34.467406+00:00",
"configuredTaskTypes": [
"text-generation"
],
@@ -56,7 +56,7 @@
"time-series-forecasting"
],
"errors": [],
"generatedAt": "2026-10-07T00:14:54.659375+00:00",
"generatedAt": "2026-10-07T00:17:34.920419+00:00",
"gpuCatalog": {
"Ascend_910-b3": {
"canVerify": true,
@@ -224,6 +224,14 @@
],
"updatedAt": "2026-10-06T22:44:08.673864+00:00"
},
"https://modelscope.cn/models/Cactus-Compute/needle3|2026-10-06T12:56:34+00:00|hygon_k100-ai": {
"taskTypes": [
"text-generation",
"text-to-image-generation",
"visual-multi-modal"
],
"updatedAt": "2026-10-07T00:17:34.920419+00:00"
},
"https://modelscope.cn/models/FINAL-Bench/Darwin-27B-RSI|2026-09-30T15:24:02+00:00|Ascend_910-b4": {
"taskTypes": [
"text-generation",
@@ -2286,14 +2294,6 @@
],
"updatedAt": "2026-10-06T22:44:08.964520+00:00"
},
"https://modelscope.cn/models/JANGQ-AI/Hy3-preview-JANGTQ_K|2026-10-06T12:53:52+00:00|MetaX_c-500": {
"taskTypes": [
"feature_emb",
"text-generation",
"visual-multi-modal"
],
"updatedAt": "2026-10-06T22:44:08.665101+00:00"
},
"https://modelscope.cn/models/JANGQ-AI/Hy3-preview-JANGTQ_K|2026-10-06T12:53:52+00:00|Mthreads_s4000": {
"taskTypes": [
"text-generation",
@@ -6439,6 +6439,6 @@
"updateTime": "2025-12-22 08:59:53"
}
],
"taskTreeUpdatedAt": "2026-10-07T00:14:54.056869+00:00",
"taskTreeUpdatedAt": "2026-10-07T00:17:34.467406+00:00",
"version": 1
}

159
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-10-07T00:04:31.120089+00:00",
"lastSyncTime": "2026-10-07T00:04:30.851007+00:00",
"generatedAt": "2026-10-07T00:15:57.133170+00:00",
"lastSyncTime": "2026-10-07T00:15:56.875101+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2301,17 +2301,19 @@
"mthreads_s4000|vllm|text-generation|model_type:qwen3_5_text": {
"architectureSignature": "model_type:qwen3_5_text",
"architectures": [],
"evidenceCount": 1,
"expiresAt": "2026-11-05T08:52:27.648162+00:00",
"evidenceCount": 2,
"expiresAt": "2026-11-05T08:52:27.660895+00:00",
"framework": "vllm",
"latestFailureAt": "2026-10-06T08:52:27.648162+00:00",
"latestFailureAt": "2026-10-06T08:52:27.660895+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "qwen3_5_text",
"sourceModelIds": [
"TokenRhythm/NeoHorse-1-4B",
"TokenRhythm/NeoHorse-1-9B"
],
"sourceTaskIds": [
"5320023",
"5320021"
],
"targetGpu": "Mthreads_s4000",
@@ -4826,15 +4828,15 @@
"unresolvedFailureCount": 158
},
"Mthreads_s4000|vllm|text-generation": {
"attributableFailureCount": 81,
"decisionFailureRate": 0.7714,
"decisionSuccessRate": 0.2286,
"decisionTotal": 105,
"attributableFailureCount": 82,
"decisionFailureRate": 0.7736,
"decisionSuccessRate": 0.2264,
"decisionTotal": 106,
"failureBreakdown": {
"ambiguous_runtime": 78,
"attention_backend": 2,
"backend_operator": 8,
"framework_architecture_unsupported": 58,
"framework_architecture_unsupported": 59,
"memory_capacity": 1,
"model_load": 3,
"platform_infrastructure": 1,
@@ -4843,17 +4845,17 @@
"tokenizer_compatibility": 3,
"参数/模板问题": 12
},
"failureCount": 172,
"failureRate": 0.8776,
"failureCount": 173,
"failureRate": 0.8782,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 24,
"successRate": 0.1224,
"successRate": 0.1218,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 196,
"total": 197,
"unresolvedFailureCount": 90
},
"Mthreads_s4000|vllm|visual-multi-modal": {
@@ -5479,17 +5481,17 @@
"unresolvedFailureCount": 6477
},
"vllm": {
"attributableFailureCount": 3667,
"attributableFailureCount": 3668,
"decisionFailureRate": 0.9722,
"decisionSuccessRate": 0.0278,
"decisionTotal": 3772,
"decisionTotal": 3773,
"failureBreakdown": {
"ambiguous_runtime": 1601,
"architecture_compatibility": 112,
"attention_backend": 3,
"backend_operator": 94,
"context_length": 161,
"framework_architecture_unsupported": 1388,
"framework_architecture_unsupported": 1389,
"memory_capacity": 725,
"model_load": 228,
"platform_infrastructure": 879,
@@ -5498,14 +5500,14 @@
"tokenizer_compatibility": 420,
"参数/模板问题": 50
},
"failureCount": 6197,
"failureCount": 6198,
"failureRate": 0.9833,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 879,
"successCount": 105,
"successRate": 0.0167,
"total": 6302,
"total": 6303,
"unresolvedFailureCount": 1651
},
"vllm-customized": {
@@ -5656,7 +5658,7 @@
"unresolvedFailureCount": 236
}
},
"generatedAt": "2026-10-07T00:04:31.102615+00:00",
"generatedAt": "2026-10-07T00:15:57.117739+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 119,
@@ -5962,15 +5964,15 @@
"unresolvedFailureCount": 767
},
"Mthreads_s4000": {
"attributableFailureCount": 85,
"decisionFailureRate": 0.6538,
"decisionSuccessRate": 0.3462,
"decisionTotal": 130,
"attributableFailureCount": 86,
"decisionFailureRate": 0.6565,
"decisionSuccessRate": 0.3435,
"decisionTotal": 131,
"failureBreakdown": {
"ambiguous_runtime": 124,
"attention_backend": 2,
"backend_operator": 8,
"framework_architecture_unsupported": 59,
"framework_architecture_unsupported": 60,
"memory_capacity": 1,
"model_load": 6,
"platform_infrastructure": 1,
@@ -5981,14 +5983,14 @@
"日志缺失": 96,
"验证失败": 26
},
"failureCount": 388,
"failureRate": 0.8961,
"failureCount": 389,
"failureRate": 0.8963,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 45,
"successRate": 0.1039,
"total": 433,
"successRate": 0.1037,
"total": 434,
"unresolvedFailureCount": 302
},
"Sunrise_pt-200-x1": {
@@ -21890,14 +21892,14 @@
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|qwen3_5_text|none": {
"attributableFailureCount": 1,
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 1
"framework_architecture_unsupported": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "qwen3_5_text",
@@ -21909,7 +21911,7 @@
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|qwen3|none": {
@@ -25599,21 +25601,21 @@
"unresolvedFailureCount": 4
},
"Mthreads_s4000|vllm|text-generation": {
"attributableFailureCount": 4,
"consecutiveFailures": 4,
"attributableFailureCount": 5,
"consecutiveFailures": 5,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 4,
"decisionTotal": 5,
"failureBreakdown": {
"ambiguous_runtime": 3,
"framework_architecture_unsupported": 4
"framework_architecture_unsupported": 5
},
"failureCount": 7,
"failureCount": 8,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-10-07T00:04:30.851007+00:00",
"lastTerminalAt": "2026-10-07T00:15:56.875101+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -25621,7 +25623,7 @@
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 7,
"total": 8,
"unresolvedFailureCount": 3
},
"Sunrise_pt-200-x1|unknown|text-generation": {
@@ -25777,18 +25779,17 @@
"unresolvedFailureCount": 6
},
"hygon_k100-ai|vllm|text-generation": {
"attributableFailureCount": 5,
"consecutiveFailures": 5,
"attributableFailureCount": 4,
"consecutiveFailures": 4,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 5,
"decisionTotal": 4,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 4,
"model_load": 1
"framework_architecture_unsupported": 4
},
"failureCount": 6,
"failureCount": 5,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -25800,7 +25801,7 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 6,
"total": 5,
"unresolvedFailureCount": 1
}
},
@@ -28806,18 +28807,18 @@
"unresolvedFailureCount": 2
},
"Mthreads_s4000|vllm|text-generation|qwen3_5_text|none": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"attributableFailureCount": 2,
"consecutiveFailures": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 1
"framework_architecture_unsupported": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"lastTerminalAt": "2026-10-07T00:04:30.851007+00:00",
"lastTerminalAt": "2026-10-07T00:15:56.875101+00:00",
"modelType": "qwen3_5_text",
"pendingCount": 0,
"pendingRate": 0.0,
@@ -28827,7 +28828,7 @@
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|starcoder2|compressed-tensors": {
@@ -53221,6 +53222,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|qwen3_5_text|none|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 32,
"modelType": "qwen3_5_text",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|qwen3_5_text|none|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -57806,20 +57831,20 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17349,
"totalRecords": 17573,
"terminalRecords": 17350,
"totalRecords": 17574,
"totals": {
"attributableFailureCount": 6237,
"decisionFailureRate": 0.8644,
"decisionSuccessRate": 0.1356,
"decisionTotal": 7215,
"attributableFailureCount": 6238,
"decisionFailureRate": 0.8645,
"decisionSuccessRate": 0.1355,
"decisionTotal": 7216,
"failureBreakdown": {
"ambiguous_runtime": 4554,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 129,
"context_length": 327,
"framework_architecture_unsupported": 2260,
"framework_architecture_unsupported": 2261,
"memory_capacity": 1206,
"model_load": 568,
"platform_infrastructure": 952,
@@ -57830,14 +57855,14 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16371,
"failureCount": 16372,
"failureRate": 0.9436,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 952,
"successCount": 978,
"successRate": 0.0564,
"total": 17349,
"total": 17350,
"unresolvedFailureCount": 9182
},
"warnings": [
@@ -57847,14 +57872,14 @@
"GPU hygon_k100-ai 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 Ascend_910-b3 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 Iluvatar_mrv-100 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 Cambricon_mlu-370-x8 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-b4 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-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。",
"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 Ascend_910-b3|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_mrv-100|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -57898,6 +57923,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17573,
"summarizedRecords": 17574,
"version": 1
}

2
.modelhub_state/recent_outcomes.jsonl
View File

@@ -1,4 +1,5 @@
{"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_fix_tokenizer", "lastSyncTime": "2026-10-06T19:00:42.266417+00:00", "modelId": "mlx-community/gpt-oss-20b-OptiQ-4bit", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11623702006, "estimatedRequiredGiB": 13.022, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 11651702017, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3982569024, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:openai", "custom_tag:gpt-oss", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:4bit", "custom_tag:mixed-precision", "custom_tag:optiq", "custom_tag:moe", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 11651702017}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T09:15:22.648982+00:00", "targetGpu": "Biren_166m", "taskId": "5320514", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_text"], "framework": "vllm", "lastSyncTime": "2026-10-07T00:15:56.875101+00:00", "modelId": "TokenRhythm/NeoHorse-1-4B", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8411552560, "estimatedRequiredGiB": 9.428, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 8435794426, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 4205751296, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agentic", "custom_tag:tool-use", "custom_tag:coding", "custom_tag:reasoning", "custom_tag:instruction-following"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8435794426}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T08:52:27.660895+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320023", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_text"], "framework": "vllm", "lastSyncTime": "2026-10-07T00:04:30.851007+00:00", "modelId": "TokenRhythm/NeoHorse-1-9B", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17907657384, "estimatedRequiredGiB": 20.04, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 17931574767, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 8953803264, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agentic", "custom_tag:tool-use", "custom_tag:coding", "custom_tag:reasoning", "custom_tag:instruction-following"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17931574767}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T08:52:27.648162+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320021", "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": "2026-10-05T02:01:26.868359+00:00", "modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-10-05T02:00:11+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4332449", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-10-04T00:08:59.465250+00:00", "modelId": "logic65/Qwen3.6-Whittle-25B-A3B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-04T00:06:57+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4593060", "taskType": "text-generation", "verifyResult": null}
@@ -297,4 +298,3 @@
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T04:51:55.164898+00:00", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T04:49:25+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4782245", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-21T04:51:55.164811+00:00", "modelId": "BAAI/Finance-llama3_1_8B_instruct", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-21T04:43:22+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4457976", "taskType": "text-generation", "verifyResult": 1}
{"failReason": "backend_operator", "failureAction": "prefer_other_proven_framework_or_gpu", "failureCategory": "backend_operator", "failureClassificationReason": "backend_version_dependent", "failureCode": "MISSING_OPERATOR", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-22T08:25:19.951625+00:00", "modelId": "RedHatAI/starcoder2-3b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4093180600, "estimatedRequiredGiB": 4.578, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 4096479058, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 3181366272, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4096479058}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T04:37:44.469638+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4993963", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-21T04:36:00.569175+00:00", "modelId": "siliconflow/Qwen3-Coder-30B-A3B-Instruct-fp8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T04:35:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4576912", "taskType": "text-generation", "verifyResult": -1}

1563
.modelhub_state/recovery_active_tasks.jsonl
View File

File diff suppressed because it is too large Load Diff

2130
.modelhub_state/recovery_intents.jsonl
View File

File diff suppressed because it is too large Load Diff