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

state: generation 7361 (intent)

Browse Source
This commit is contained in:
CoolBoy
2026-09-14 20:41:42 +00:00
parent b32f90ab6f
commit 865521cbdb
8 changed files with 860 additions and 859 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -1548,7 +1548,7 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-09-14T20:38:17.503352+00:00", "generatedAt": "2026-09-14T20:39:18.753775+00:00",
"summary": { "summary": {
"activeBlockCount": 77, "activeBlockCount": 77,
"byGpuFramework": { "byGpuFramework": {

6
.modelhub_state/market_intelligence.json
View File

@@ -1,8 +1,8 @@
{ {
"communityAttemptedAt": "2026-09-14T20:21:49.733990+00:00", "communityAttemptedAt": "2026-09-14T20:39:26.664466+00:00",
"communityError": null, "communityError": null,
"communitySample": {}, "communitySample": {},
"communityUpdatedAt": "2026-09-14T20:21:49.733990+00:00", "communityUpdatedAt": "2026-09-14T20:39:26.664466+00:00",
"frameworkAttemptedAt": "2026-09-14T14:53:04.199321+00:00", "frameworkAttemptedAt": "2026-09-14T14:53:04.199321+00:00",
"frameworkError": null, "frameworkError": null,
"frameworkStats": { "frameworkStats": {
@@ -416,7 +416,7 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-09-14T20:36:34.480631+00:00", "generatedAt": "2026-09-14T20:39:26.664466+00:00",
"gpuStats": { "gpuStats": {
"Ascend_910-b3": { "Ascend_910-b3": {
"available": true, "available": true,

1534
.modelhub_state/official_capabilities.json
View File

File diff suppressed because it is too large Load Diff

147
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{ {
"generatedAt": "2026-09-14T19:41:18.806767+00:00", "generatedAt": "2026-09-14T20:39:18.720855+00:00",
"lastSyncTime": "2026-09-14T19:41:18.606689+00:00", "lastSyncTime": "2026-09-14T20:39:18.216520+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -1779,29 +1779,29 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Cambricon_mlu-370-x4|unknown|text-generation": { "Cambricon_mlu-370-x4|unknown|text-generation": {
"attributableFailureCount": 22, "attributableFailureCount": 23,
"decisionFailureRate": 0.9167, "decisionFailureRate": 0.92,
"decisionSuccessRate": 0.0833, "decisionSuccessRate": 0.08,
"decisionTotal": 24, "decisionTotal": 25,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 36, "ambiguous_runtime": 36,
"framework_architecture_unsupported": 20, "framework_architecture_unsupported": 20,
"memory_capacity": 1, "memory_capacity": 1,
"tokenizer_compatibility": 1, "tokenizer_compatibility": 2,
"参数/模板问题": 1, "参数/模板问题": 1,
"验证失败": 39 "验证失败": 39
}, },
"failureCount": 98, "failureCount": 99,
"failureRate": 0.98, "failureRate": 0.9802,
"framework": "unknown", "framework": "unknown",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 2, "successCount": 2,
"successRate": 0.02, "successRate": 0.0198,
"targetGpu": "Cambricon_mlu-370-x4", "targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation", "taskType": "text-generation",
"total": 100, "total": 101,
"unresolvedFailureCount": 76 "unresolvedFailureCount": 76
}, },
"Cambricon_mlu-370-x8|unknown|text-generation": { "Cambricon_mlu-370-x8|unknown|text-generation": {
@@ -1989,25 +1989,25 @@
"decisionSuccessRate": 0.1875, "decisionSuccessRate": 0.1875,
"decisionTotal": 16, "decisionTotal": 16,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 6, "ambiguous_runtime": 7,
"backend_operator": 4, "backend_operator": 4,
"framework_architecture_unsupported": 5, "framework_architecture_unsupported": 5,
"model_load": 2, "model_load": 2,
"runtime_memory": 2, "runtime_memory": 2,
"参数/模板问题": 1 "参数/模板问题": 1
}, },
"failureCount": 20, "failureCount": 21,
"failureRate": 0.8696, "failureRate": 0.875,
"framework": "vllm_0_17_0_corex_4_4_0", "framework": "vllm_0_17_0_corex_4_4_0",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 3, "successCount": 3,
"successRate": 0.1304, "successRate": 0.125,
"targetGpu": "Iluvatar_bi-150", "targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation", "taskType": "text-generation",
"total": 23, "total": 24,
"unresolvedFailureCount": 7 "unresolvedFailureCount": 8
}, },
"Iluvatar_bi-150|vllm|text-generation": { "Iluvatar_bi-150|vllm|text-generation": {
"attributableFailureCount": 26, "attributableFailureCount": 26,
@@ -2564,10 +2564,10 @@
"unresolvedFailureCount": 8 "unresolvedFailureCount": 8
}, },
"unknown": { "unknown": {
"attributableFailureCount": 161, "attributableFailureCount": 162,
"decisionFailureRate": 0.7419, "decisionFailureRate": 0.7431,
"decisionSuccessRate": 0.2581, "decisionSuccessRate": 0.2569,
"decisionTotal": 217, "decisionTotal": 218,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 151, "ambiguous_runtime": 151,
"backend_operator": 4, "backend_operator": 4,
@@ -2575,18 +2575,18 @@
"memory_capacity": 5, "memory_capacity": 5,
"model_load": 45, "model_load": 45,
"platform_infrastructure": 1, "platform_infrastructure": 1,
"tokenizer_compatibility": 3, "tokenizer_compatibility": 4,
"参数/模板问题": 66, "参数/模板问题": 66,
"验证失败": 673 "验证失败": 673
}, },
"failureCount": 1052, "failureCount": 1053,
"failureRate": 0.9495, "failureRate": 0.9495,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 1, "platformFailureCount": 1,
"successCount": 56, "successCount": 56,
"successRate": 0.0505, "successRate": 0.0505,
"total": 1108, "total": 1109,
"unresolvedFailureCount": 890 "unresolvedFailureCount": 890
}, },
"vllm": { "vllm": {
@@ -2662,22 +2662,22 @@
"decisionSuccessRate": 0.1875, "decisionSuccessRate": 0.1875,
"decisionTotal": 16, "decisionTotal": 16,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 6, "ambiguous_runtime": 7,
"backend_operator": 4, "backend_operator": 4,
"framework_architecture_unsupported": 5, "framework_architecture_unsupported": 5,
"model_load": 2, "model_load": 2,
"runtime_memory": 2, "runtime_memory": 2,
"参数/模板问题": 1 "参数/模板问题": 1
}, },
"failureCount": 20, "failureCount": 21,
"failureRate": 0.8696, "failureRate": 0.875,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 3, "successCount": 3,
"successRate": 0.1304, "successRate": 0.125,
"total": 23, "total": 24,
"unresolvedFailureCount": 7 "unresolvedFailureCount": 8
}, },
"vllm_fix_tokenizer": { "vllm_fix_tokenizer": {
"attributableFailureCount": 53, "attributableFailureCount": 53,
@@ -2722,7 +2722,7 @@
"unresolvedFailureCount": 1 "unresolvedFailureCount": 1
} }
}, },
"generatedAt": "2026-09-14T19:41:18.800840+00:00", "generatedAt": "2026-09-14T20:39:18.716063+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 36, "attributableFailureCount": 36,
@@ -2798,26 +2798,26 @@
"unresolvedFailureCount": 59 "unresolvedFailureCount": 59
}, },
"Cambricon_mlu-370-x4": { "Cambricon_mlu-370-x4": {
"attributableFailureCount": 22, "attributableFailureCount": 23,
"decisionFailureRate": 0.9167, "decisionFailureRate": 0.92,
"decisionSuccessRate": 0.0833, "decisionSuccessRate": 0.08,
"decisionTotal": 24, "decisionTotal": 25,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 36, "ambiguous_runtime": 36,
"framework_architecture_unsupported": 20, "framework_architecture_unsupported": 20,
"memory_capacity": 1, "memory_capacity": 1,
"tokenizer_compatibility": 1, "tokenizer_compatibility": 2,
"参数/模板问题": 1, "参数/模板问题": 1,
"验证失败": 39 "验证失败": 39
}, },
"failureCount": 98, "failureCount": 99,
"failureRate": 0.98, "failureRate": 0.9802,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 2, "successCount": 2,
"successRate": 0.02, "successRate": 0.0198,
"total": 100, "total": 101,
"unresolvedFailureCount": 76 "unresolvedFailureCount": 76
}, },
"Cambricon_mlu-370-x8": { "Cambricon_mlu-370-x8": {
@@ -2868,7 +2868,7 @@
"decisionSuccessRate": 0.1837, "decisionSuccessRate": 0.1837,
"decisionTotal": 49, "decisionTotal": 49,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 14, "ambiguous_runtime": 15,
"backend_operator": 7, "backend_operator": 7,
"framework_architecture_unsupported": 19, "framework_architecture_unsupported": 19,
"model_load": 9, "model_load": 9,
@@ -2877,15 +2877,15 @@
"参数/模板问题": 3, "参数/模板问题": 3,
"验证失败": 30 "验证失败": 30
}, },
"failureCount": 87, "failureCount": 88,
"failureRate": 0.9062, "failureRate": 0.9072,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 9, "successCount": 9,
"successRate": 0.0938, "successRate": 0.0928,
"total": 96, "total": 97,
"unresolvedFailureCount": 47 "unresolvedFailureCount": 48
}, },
"Iluvatar_mrv-100": { "Iluvatar_mrv-100": {
"attributableFailureCount": 101, "attributableFailureCount": 101,
@@ -3766,10 +3766,11 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 2, "decisionTotal": 2,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 1,
"backend_operator": 1, "backend_operator": 1,
"runtime_memory": 1 "runtime_memory": 1
}, },
"failureCount": 2, "failureCount": 3,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0", "framework": "vllm_0_17_0_corex_4_4_0",
"modelType": "qwen3_5", "modelType": "qwen3_5",
@@ -3781,8 +3782,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Iluvatar_bi-150", "targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation", "taskType": "text-generation",
"total": 2, "total": 3,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 1
}, },
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|escha": { "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|escha": {
"attributableFailureCount": 1, "attributableFailureCount": 1,
@@ -5365,22 +5366,23 @@
"unresolvedFailureCount": 11 "unresolvedFailureCount": 11
}, },
"Cambricon_mlu-370-x4|unknown|text-generation": { "Cambricon_mlu-370-x4|unknown|text-generation": {
"attributableFailureCount": 2, "attributableFailureCount": 3,
"consecutiveFailures": 2, "consecutiveFailures": 3,
"consecutivePlatformFailures": 0, "consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 2, "decisionTotal": 3,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 17, "ambiguous_runtime": 16,
"framework_architecture_unsupported": 2, "framework_architecture_unsupported": 2,
"tokenizer_compatibility": 1,
"参数/模板问题": 1 "参数/模板问题": 1
}, },
"failureCount": 20, "failureCount": 20,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "unknown", "framework": "unknown",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-14T18:50:27.851919+00:00", "lastTerminalAt": "2026-09-14T20:39:18.216520+00:00",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
@@ -5389,7 +5391,7 @@
"targetGpu": "Cambricon_mlu-370-x4", "targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation", "taskType": "text-generation",
"total": 20, "total": 20,
"unresolvedFailureCount": 18 "unresolvedFailureCount": 17
}, },
"Cambricon_mlu-370-x8|unknown|text-generation": { "Cambricon_mlu-370-x8|unknown|text-generation": {
"attributableFailureCount": 1, "attributableFailureCount": 1,
@@ -6801,9 +6803,10 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 1, "decisionTotal": 1,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 1,
"runtime_memory": 1 "runtime_memory": 1
}, },
"failureCount": 1, "failureCount": 2,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0", "framework": "vllm_0_17_0_corex_4_4_0",
"loadSizeLog2Bucket": 34, "loadSizeLog2Bucket": 34,
@@ -6816,8 +6819,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Iluvatar_bi-150", "targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation", "taskType": "text-generation",
"total": 1, "total": 2,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 1
}, },
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|escha|33": { "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|escha|33": {
"attributableFailureCount": 1, "attributableFailureCount": 1,
@@ -8929,15 +8932,15 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 1866, "terminalRecords": 1868,
"totalRecords": 1959, "totalRecords": 1961,
"totals": { "totals": {
"attributableFailureCount": 564, "attributableFailureCount": 565,
"decisionFailureRate": 0.8995, "decisionFailureRate": 0.8997,
"decisionSuccessRate": 0.1005, "decisionSuccessRate": 0.1003,
"decisionTotal": 627, "decisionTotal": 628,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 444, "ambiguous_runtime": 445,
"backend_operator": 44, "backend_operator": 44,
"framework_architecture_unsupported": 361, "framework_architecture_unsupported": 361,
"memory_capacity": 12, "memory_capacity": 12,
@@ -8945,19 +8948,19 @@
"platform_infrastructure": 6, "platform_infrastructure": 6,
"repository_structure": 8, "repository_structure": 8,
"runtime_memory": 8, "runtime_memory": 8,
"tokenizer_compatibility": 53, "tokenizer_compatibility": 54,
"参数/模板问题": 116, "参数/模板问题": 116,
"验证失败": 673 "验证失败": 673
}, },
"failureCount": 1803, "failureCount": 1805,
"failureRate": 0.9662, "failureRate": 0.9663,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 6, "platformFailureCount": 6,
"successCount": 63, "successCount": 63,
"successRate": 0.0338, "successRate": 0.0337,
"total": 1866, "total": 1868,
"unresolvedFailureCount": 1233 "unresolvedFailureCount": 1234
}, },
"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。",
@@ -8995,6 +8998,6 @@
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 1959, "summarizedRecords": 1961,
"version": 1 "version": 1
} }

2
.modelhub_state/recent_outcomes.jsonl
View File

@@ -1,3 +1,4 @@
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "", "lastSyncTime": "2026-09-14T20:39:18.216520+00:00", "modelId": "zstack/qwen3-4b-fake", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T20:33:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4582857", "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"], "framework": "vllm", "lastSyncTime": "2026-09-14T19:09:56.106622+00:00", "modelId": "groxaxo/Qwen3.8-27B-GPTQ-Pro-4bit-g64-calib128", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T19:05:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4591690", "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"], "framework": "vllm", "lastSyncTime": "2026-09-14T19:09:56.106622+00:00", "modelId": "groxaxo/Qwen3.8-27B-GPTQ-Pro-4bit-g64-calib128", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T19:05:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4591690", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-14T18:50:27.851828+00:00", "modelId": "empero-ai/Qwen3.8-9B-Distill", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-14T18:42:41+00:00", "targetGpu": "Biren_166m", "taskId": "4610391", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-14T18:50:27.851828+00:00", "modelId": "empero-ai/Qwen3.8-9B-Distill", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-14T18:42:41+00:00", "targetGpu": "Biren_166m", "taskId": "4610391", "taskType": "text-generation", "verifyResult": null}
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-14T18:50:27.851864+00:00", "modelId": "empero-ai/Qwen3.8-9B-Distill", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-14T18:42:41+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4592743", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-14T18:50:27.851864+00:00", "modelId": "empero-ai/Qwen3.8-9B-Distill", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-14T18:42:41+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4592743", "taskType": "text-generation", "verifyResult": null}
@@ -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": "", "lastSyncTime": "2026-09-10T01:50:54.936003+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T01:49:21+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4481654", "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": "2026-09-10T01:50:54.936003+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T01:49:21+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4481654", "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": "2026-09-10T01:50:54.936024+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T01:43:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4596146", "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": "2026-09-10T01:50:54.936024+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T01:43:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4596146", "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": "2026-09-10T01:42:34.770281+00:00", "modelId": "nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t-alt", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T01:37:21+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4481718", "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": "2026-09-10T01:42:34.770281+00:00", "modelId": "nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t-alt", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T01:37:21+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4481718", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T01:16:26.008857+00:00", "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T01:13:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505087", "taskType": "text-generation", "verifyResult": -1}

1
.modelhub_state/recovery_intents.jsonl
View File

@@ -761,6 +761,7 @@
{"batchId": "2e167d4064f54fe18b5ee112a7f1b28e", "completedAt": "2026-09-14T20:21:45.411039+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-14T20:21:38.335355+00:00", "framework": "vllm_tokenizer_patch", "intentId": "9ba0b97d0fe44a3cb473f832d19e9617", "lastModified": "2026-09-14T20:10:09+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit", "reason": null, "reconciledAt": "2026-09-14T20:36:31.740000+00:00", "repoId": "mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "4856789", "taskType": "text-generation"} {"batchId": "2e167d4064f54fe18b5ee112a7f1b28e", "completedAt": "2026-09-14T20:21:45.411039+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-14T20:21:38.335355+00:00", "framework": "vllm_tokenizer_patch", "intentId": "9ba0b97d0fe44a3cb473f832d19e9617", "lastModified": "2026-09-14T20:10:09+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit", "reason": null, "reconciledAt": "2026-09-14T20:36:31.740000+00:00", "repoId": "mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "4856789", "taskType": "text-generation"}
{"batchId": "57c4f72db8c04131b3b27b51ae3b13c4", "completedAt": "2026-09-14T20:23:40.211564+00:00", "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configSource": "modelhub_live", "createdAt": "2026-09-14T20:23:33.269434+00:00", "framework": "vllm", "intentId": "e770650d5fcb44d4b8515a118a4b48b5", "lastModified": "2026-09-14T10:29:22+00:00", "modelAddress": "https://modelscope.cn/models/hcnote/SparkMuse-4B", "reason": null, "reconciledAt": "2026-09-14T20:36:31.739408+00:00", "repoId": "hcnote/SparkMuse-4B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "4856813", "taskType": "text-generation"} {"batchId": "57c4f72db8c04131b3b27b51ae3b13c4", "completedAt": "2026-09-14T20:23:40.211564+00:00", "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configSource": "modelhub_live", "createdAt": "2026-09-14T20:23:33.269434+00:00", "framework": "vllm", "intentId": "e770650d5fcb44d4b8515a118a4b48b5", "lastModified": "2026-09-14T10:29:22+00:00", "modelAddress": "https://modelscope.cn/models/hcnote/SparkMuse-4B", "reason": null, "reconciledAt": "2026-09-14T20:36:31.739408+00:00", "repoId": "hcnote/SparkMuse-4B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "4856813", "taskType": "text-generation"}
{"batchId": "8a2e4e7ca458414b97328d30f031c650", "completedAt": "2026-09-14T20:36:30.466722+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-14T20:36:22.416710+00:00", "framework": "vllm_tokenizer_patch", "intentId": "12c4caf914ee444b8b4337db3ebc93fb", "lastModified": "2026-09-14T20:27:07+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "reason": null, "reconciledAt": "2026-09-14T20:36:31.739111+00:00", "repoId": "mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "4856934", "taskType": "text-generation"} {"batchId": "8a2e4e7ca458414b97328d30f031c650", "completedAt": "2026-09-14T20:36:30.466722+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-14T20:36:22.416710+00:00", "framework": "vllm_tokenizer_patch", "intentId": "12c4caf914ee444b8b4337db3ebc93fb", "lastModified": "2026-09-14T20:27:07+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "reason": null, "reconciledAt": "2026-09-14T20:36:31.739111+00:00", "repoId": "mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "4856934", "taskType": "text-generation"}
{"batchId": "2417306ee65f42ec9dc3a415a067e17f", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-14T20:41:42.447811+00:00", "framework": "vllm-mlu", "intentId": "d1a2df4492c2467f927253f4231b1da7", "lastModified": "2026-09-14T10:29:22+00:00", "modelAddress": "https://modelscope.cn/models/hcnote/SparkMuse-4B", "repoId": "hcnote/SparkMuse-4B", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
{"batchId": "83639d5151dd4bb78879458f9850c53a", "completedAt": "2026-09-14T06:07:56.622377+00:00", "configFingerprint": "e4588bdbccc377f0f7599581ea0752e64b81eda54f82b575b6aaa81c27ce2e73", "configSource": "modelhub_live", "createdAt": "2026-09-14T06:07:48.751836+00:00", "framework": "llamacpp", "intentId": "35fd7d8028f54640b4d005111704edc0", "repoId": "voconly/nemotron-3.5-asr-streaming-0.6b-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} {"batchId": "83639d5151dd4bb78879458f9850c53a", "completedAt": "2026-09-14T06:07:56.622377+00:00", "configFingerprint": "e4588bdbccc377f0f7599581ea0752e64b81eda54f82b575b6aaa81c27ce2e73", "configSource": "modelhub_live", "createdAt": "2026-09-14T06:07:48.751836+00:00", "framework": "llamacpp", "intentId": "35fd7d8028f54640b4d005111704edc0", "repoId": "voconly/nemotron-3.5-asr-streaming-0.6b-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "9ea43510e22a43e9991959f19dd0f4a2", "completedAt": "2026-09-13T12:43:37.101071+00:00", "configFingerprint": "7d273c6d9a11c4e826d64fc44d3ae14d805bd3b1e6e663d4dd0b45567cfc5e3f", "configSource": "modelhub_live", "createdAt": "2026-09-13T12:43:27.207464+00:00", "framework": "llamacpp", "intentId": "ab083753c716462fbb8b0529ac182658", "repoId": "voconly/nemotron-3.5-asr-streaming-0.6b-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "uniqueness_rejected", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"} {"batchId": "9ea43510e22a43e9991959f19dd0f4a2", "completedAt": "2026-09-13T12:43:37.101071+00:00", "configFingerprint": "7d273c6d9a11c4e826d64fc44d3ae14d805bd3b1e6e663d4dd0b45567cfc5e3f", "configSource": "modelhub_live", "createdAt": "2026-09-13T12:43:27.207464+00:00", "framework": "llamacpp", "intentId": "ab083753c716462fbb8b0529ac182658", "repoId": "voconly/nemotron-3.5-asr-streaming-0.6b-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "uniqueness_rejected", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"}
{"batchId": "9370c3290d2242cebbdd1924870f426b", "completedAt": "2026-09-13T12:41:31.618354+00:00", "configFingerprint": "d7cf4e4fcae21f022bbcb9f71b3bb0ab37d6331cf8fd1cd3ad4ba75043690051", "configSource": "modelhub_live", "createdAt": "2026-09-13T12:41:17.857077+00:00", "framework": "llamacpp", "intentId": "8c62b06728694cd9b6f7c5c378f53285", "repoId": "voconly/nemotron-3.5-asr-streaming-0.6b-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "9370c3290d2242cebbdd1924870f426b", "completedAt": "2026-09-13T12:41:31.618354+00:00", "configFingerprint": "d7cf4e4fcae21f022bbcb9f71b3bb0ab37d6331cf8fd1cd3ad4ba75043690051", "configSource": "modelhub_live", "createdAt": "2026-09-13T12:41:17.857077+00:00", "framework": "llamacpp", "intentId": "8c62b06728694cd9b6f7c5c378f53285", "repoId": "voconly/nemotron-3.5-asr-streaming-0.6b-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}

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": "36dd1c5c8b738f15fa831ce10a02dcd5108939aeaa3eaad111694414a1366b76", ".modelhub_state/architecture_compatibility_blacklist.json": "71280b83fe993750a87c394c4796c69cbbdf7bf5041243dc2f53a392000f621a",
".modelhub_state/architecture_history_backfill.json": "003bb3e915da3fe2a7e7d6dc14f632226b3c9ae960f3e13ac6df2ad1b246e5c2", ".modelhub_state/architecture_history_backfill.json": "003bb3e915da3fe2a7e7d6dc14f632226b3c9ae960f3e13ac6df2ad1b246e5c2",
".modelhub_state/market_intelligence.json": "22e78b91e7795bf23c1f36ad9bd604c99dd3f24bf46844daf0b80fd7b42e08aa", ".modelhub_state/market_intelligence.json": "27eace97a240343bf598c60aaa53179325f392fa4b2907c4db606efc22549f4c",
".modelhub_state/official_capabilities.json": "2ff1faacb42acba5ad175d672acb82e70e384c92a77f654ba15a830e50cc7d92", ".modelhub_state/official_capabilities.json": "1215445f6310706614bc830f946d0fd811d4c50eadb417e1535d6794524f5f1a",
".modelhub_state/outcome_checkpoint.json": "aaf006c1f34b5bd512d08218b17a48b2a123d9b19d8b239933a379de9849ce68", ".modelhub_state/outcome_checkpoint.json": "95dcf47c5e0d92919a2ca9f1dd24ceef65ec5816c39834e59e99751764ab455b",
".modelhub_state/queue_cleanup_latest.json": "2db00f279cdac43f8f1cc1f62cd63046aca30c207631791fe39472e61beff82c", ".modelhub_state/queue_cleanup_latest.json": "2db00f279cdac43f8f1cc1f62cd63046aca30c207631791fe39472e61beff82c",
".modelhub_state/recent_outcomes.jsonl": "3e24fc4737c55e3b6e844dc62b00d58cb1695b8187a84877e351d8333743bcd4", ".modelhub_state/recent_outcomes.jsonl": "b921ca2b3fc890450c7f8cb499d9276e378f24daa5604149a57497af85d6df88",
".modelhub_state/recovery_active_tasks.jsonl": "7eaf3ea0603a40074ef871a64524e43b9350f266aa005b18e131dbc44d208b31", ".modelhub_state/recovery_active_tasks.jsonl": "7eaf3ea0603a40074ef871a64524e43b9350f266aa005b18e131dbc44d208b31",
".modelhub_state/recovery_intents.jsonl": "d613f90b1ee4989ed3b8e357386cab828e5fbefc269fbef7d22b9b8e4cb63257", ".modelhub_state/recovery_intents.jsonl": "1c4434348cf009b5bc50eee85854edb067325ce47c7d6b61d759b4f62a6e74bf",
".modelhub_state/routing_intelligence.json": "2d0bb257007589d83aefe81955c4a51b39a9ada73ed15c816546b52dd69a01f1", ".modelhub_state/routing_intelligence.json": "2d0bb257007589d83aefe81955c4a51b39a9ada73ed15c816546b52dd69a01f1",
".modelhub_state/submission_exclusions.jsonl": "632739c6cd6a2dd2237572ba18e6a390c5aa37ce56a18a2c1341d78569421552", ".modelhub_state/submission_exclusions.jsonl": "632739c6cd6a2dd2237572ba18e6a390c5aa37ce56a18a2c1341d78569421552",
".modelhub_state/worker_crashes.jsonl": "53505d335313446ff7094bcb58658b561de55799302fa7bfb49e418e414eebad", ".modelhub_state/worker_crashes.jsonl": "53505d335313446ff7094bcb58658b561de55799302fa7bfb49e418e414eebad",
"ledger/submissions.jsonl": "433507be6fbfc20919da09f01e137003e2e6efba86374c732fc660f1993dd75c", "ledger/submissions.jsonl": "433507be6fbfc20919da09f01e137003e2e6efba86374c732fc660f1993dd75c",
"outcomes/submissions.jsonl": "a80e64f09b55b926d67d29d278c107cb2cbc2350339e29e5112ee5d2d809566d" "outcomes/submissions.jsonl": "12e56062549315b422a28e50ec8820d85694ef28af1a987a6c9454d5912277f3"
}, },
"generation": 7360, "generation": 7361,
"phase": "cycle", "phase": "intent",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-09-14T20:38:17.602246+00:00", "updatedAt": "2026-09-14T20:41:42.560508+00:00",
"writerId": "69701e73196b4ac2b3fad0f412335168" "writerId": "69701e73196b4ac2b3fad0f412335168"
} }

7
outcomes/submissions.jsonl
View File

@@ -99,7 +99,6 @@
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T20:12:28.913845+00:00", "modelId": "LiquidAI/LFM2.5-8B-A1B-DSpark-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "e023b149992af42872de3c0c0c07dafd6a98d965e5bdb5a29ec5869e58d45725", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 356491104, "estimatedRequiredGiB": 1.363, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 1219879026, "modelscopeLicense": "other", "modelscopeParams": 327707521, "modelscopeTags": ["license:other", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:speculative-decoding", "custom_tag:dspark", "custom_tag:lfm2", "custom_tag:draft-model", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1219879026}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T12:03:37.084154+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4648146", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T20:12:28.913845+00:00", "modelId": "LiquidAI/LFM2.5-8B-A1B-DSpark-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "e023b149992af42872de3c0c0c07dafd6a98d965e5bdb5a29ec5869e58d45725", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 356491104, "estimatedRequiredGiB": 1.363, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 1219879026, "modelscopeLicense": "other", "modelscopeParams": 327707521, "modelscopeTags": ["license:other", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:speculative-decoding", "custom_tag:dspark", "custom_tag:lfm2", "custom_tag:draft-model", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1219879026}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T12:03:37.084154+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4648146", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T20:12:28.913926+00:00", "modelId": "siliconflow/Qwen3-Coder-30B-A3B-Instruct-fp8", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 31263441624, "estimatedRequiredGiB": 34.958, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 31280205657, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 30554505408, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_moe", "library:safetensors", "library:other", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 31280205657}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T12:03:37.105603+00:00", "targetGpu": "MetaX_c-500", "taskId": "4648141", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T20:12:28.913926+00:00", "modelId": "siliconflow/Qwen3-Coder-30B-A3B-Instruct-fp8", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 31263441624, "estimatedRequiredGiB": 34.958, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 31280205657, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 30554505408, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_moe", "library:safetensors", "library:other", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 31280205657}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T12:03:37.105603+00:00", "targetGpu": "MetaX_c-500", "taskId": "4648141", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T21:15:28.523439+00:00", "modelId": "LiquidAI/LFM2.5-8B-A1B-DSpark-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "0dce7c4be445254429760db90c7969177ecdca460563778d8b3371a37cc1a50e", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 356491104, "estimatedRequiredGiB": 1.363, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 1219879026, "modelscopeLicense": "other", "modelscopeParams": 327707521, "modelscopeTags": ["license:other", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:speculative-decoding", "custom_tag:dspark", "custom_tag:lfm2", "custom_tag:draft-model", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1219879026}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T13:07:23.099409+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4649238", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T21:15:28.523439+00:00", "modelId": "LiquidAI/LFM2.5-8B-A1B-DSpark-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "0dce7c4be445254429760db90c7969177ecdca460563778d8b3371a37cc1a50e", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 356491104, "estimatedRequiredGiB": 1.363, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 1219879026, "modelscopeLicense": "other", "modelscopeParams": 327707521, "modelscopeTags": ["license:other", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:speculative-decoding", "custom_tag:dspark", "custom_tag:lfm2", "custom_tag:draft-model", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1219879026}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T13:07:23.099409+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4649238", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-05T21:15:28.523422+00:00", "modelId": "douyamv/Qwen3.8-27B-FP8", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 28178526992, "estimatedRequiredGiB": 31.518, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 28201576294, "modelscopeLicense": "apache-2.0", "modelscopeParams": 26895998464, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:fp8", "custom_tag:quantized", "custom_tag:vllm", "custom_tag:safetensors"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 28201576294}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T13:07:23.110104+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4649235", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-05T21:15:28.523404+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8818103892, "estimatedRequiredGiB": 9.883, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 8842796317, "modelscopeLicense": "mit", "modelscopeParams": 6728625904, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 8842796317}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T13:07:29.655509+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4649242", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-05T21:15:28.523404+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8818103892, "estimatedRequiredGiB": 9.883, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 8842796317, "modelscopeLicense": "mit", "modelscopeParams": 6728625904, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 8842796317}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T13:07:29.655509+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4649242", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-05T21:15:28.523467+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8991501632, "estimatedRequiredGiB": 10.084, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9023443508, "modelscopeLicense": "mit", "modelscopeParams": 9409813744, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9023443508}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T13:07:29.759253+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4649244", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-05T21:15:28.523467+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8991501632, "estimatedRequiredGiB": 10.084, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9023443508, "modelscopeLicense": "mit", "modelscopeParams": 9409813744, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9023443508}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T13:07:29.759253+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4649244", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-05T21:15:28.523345+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-MLX-8bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9514532079, "estimatedRequiredGiB": 10.658, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9536343971, "modelscopeLicense": null, "modelscopeParams": 2519020032, "modelscopeTags": ["model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9536343971}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T13:15:06.885148+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4649368", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-05T21:15:28.523345+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-MLX-8bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9514532079, "estimatedRequiredGiB": 10.658, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9536343971, "modelscopeLicense": null, "modelscopeParams": 2519020032, "modelscopeTags": ["model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9536343971}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T13:15:06.885148+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4649368", "taskType": "text-generation", "verifyResult": null}
@@ -619,9 +618,9 @@
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-14T17:53:12.698106+00:00", "modelId": "mlx-community/Agents-A1-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13249080076, "estimatedRequiredGiB": 14.83, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13269528840, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13269528840}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T09:49:08.451908+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4847129", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-14T17:53:12.698106+00:00", "modelId": "mlx-community/Agents-A1-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13249080076, "estimatedRequiredGiB": 14.83, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13269528840, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13269528840}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T09:49:08.451908+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4847129", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-14T18:50:27.851852+00:00", "modelId": "aucaCQS/Spark-X2.5-4B-Coder-Flash", "modelProfile": {"architectures": [], "configFingerprint": "6270b79db6f53655ba1dc1b7e093937b145df2e6fa5dc1d91f6c309d1008d815", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021120, "estimatedRequiredGiB": 37.948, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 32173498806, "modelscopeLicense": null, "modelscopeParams": 4112079360, "modelscopeTags": ["library:gguf", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 33955496536}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T10:42:38.360078+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4847818", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-14T18:50:27.851852+00:00", "modelId": "aucaCQS/Spark-X2.5-4B-Coder-Flash", "modelProfile": {"architectures": [], "configFingerprint": "6270b79db6f53655ba1dc1b7e093937b145df2e6fa5dc1d91f6c309d1008d815", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021120, "estimatedRequiredGiB": 37.948, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 32173498806, "modelscopeLicense": null, "modelscopeParams": 4112079360, "modelscopeTags": ["library:gguf", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 33955496536}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T10:42:38.360078+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4847818", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-14T19:09:56.106587+00:00", "modelId": "aucaCQS/Spark-X2.5-4B-Coder-Flash", "modelProfile": {"architectures": [], "configFingerprint": "f0079c5722ce37ff9d929e5e96de8925a4670b711936f17faab5f7565f2ecb43", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021120, "estimatedRequiredGiB": 37.948, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 32173498806, "modelscopeLicense": null, "modelscopeParams": 4112079360, "modelscopeTags": ["library:gguf", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 33955496536}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T10:59:43.480777+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4847964", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-14T19:09:56.106587+00:00", "modelId": "aucaCQS/Spark-X2.5-4B-Coder-Flash", "modelProfile": {"architectures": [], "configFingerprint": "f0079c5722ce37ff9d929e5e96de8925a4670b711936f17faab5f7565f2ecb43", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021120, "estimatedRequiredGiB": 37.948, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 32173498806, "modelscopeLicense": null, "modelscopeParams": 4112079360, "modelscopeTags": ["library:gguf", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 33955496536}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T10:59:43.480777+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4847964", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": null, "modelId": "aucaCQS/Spark-X2.5-4B-Coder-Flash", "modelProfile": {"architectures": [], "configFingerprint": "327b4fcce82afa7c692364047b27c53d2b6ae7a0f2522806938c3c935ae9a735", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021120, "estimatedRequiredGiB": 37.948, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 33955496529, "modelscopeLicense": null, "modelscopeParams": 4112079360, "modelscopeTags": ["library:gguf", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 33955496529}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-14T12:34:59.173731+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4849005", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-14T20:39:18.216494+00:00", "modelId": "aucaCQS/Spark-X2.5-4B-Coder-Flash", "modelProfile": {"architectures": [], "configFingerprint": "327b4fcce82afa7c692364047b27c53d2b6ae7a0f2522806938c3c935ae9a735", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021120, "estimatedRequiredGiB": 37.948, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 33955496529, "modelscopeLicense": null, "modelscopeParams": 4112079360, "modelscopeTags": ["library:gguf", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 33955496529}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T12:34:59.173731+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4849005", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "Edge0/Edge0-35B-A3B-preview", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19689863445, "estimatedRequiredGiB": 22.059, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 19738195355, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5419330688, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:lora", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:edge-inference", "custom_tag:prerouter", "custom_tag:lora", "custom_tag:ssd-offload"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19738195355}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-14T12:34:59.176520+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4849007", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-14T20:39:18.216500+00:00", "modelId": "Edge0/Edge0-35B-A3B-preview", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19689863445, "estimatedRequiredGiB": 22.059, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 19738195355, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5419330688, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:lora", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:edge-inference", "custom_tag:prerouter", "custom_tag:lora", "custom_tag:ssd-offload"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19738195355}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T12:34:59.176520+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4849007", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "mlx-community/Agents-A1-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13249080076, "estimatedRequiredGiB": 14.83, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13269528840, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13269528840}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-14T12:34:59.178065+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4849006", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-14T20:39:18.216485+00:00", "modelId": "mlx-community/Agents-A1-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13249080076, "estimatedRequiredGiB": 14.83, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13269528840, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13269528840}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T12:34:59.178065+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4849006", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "yujianboisme/qwen2.5-1.5b-darkhorse-code-fine-tuning", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3087467712, "estimatedRequiredGiB": 3.468, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 802490000, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1543714304, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:text-generation", "custom_tag:qwen2.5", "custom_tag:lora", "custom_tag:json", "custom_tag:instruction-following", "custom_tag:chinese", "custom_tag:command-translation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3103395696}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-14T13:50:28.944104+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4849951", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "yujianboisme/qwen2.5-1.5b-darkhorse-code-fine-tuning", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3087467712, "estimatedRequiredGiB": 3.468, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 802490000, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1543714304, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:text-generation", "custom_tag:qwen2.5", "custom_tag:lora", "custom_tag:json", "custom_tag:instruction-following", "custom_tag:chinese", "custom_tag:command-translation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3103395696}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-14T13:50:28.944104+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4849951", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "yujianboisme/qwen2.5-1.5b-darkhorse-code-fine-tuning", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3087467712, "estimatedRequiredGiB": 3.468, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 802490000, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1543714304, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:text-generation", "custom_tag:qwen2.5", "custom_tag:lora", "custom_tag:json", "custom_tag:instruction-following", "custom_tag:chinese", "custom_tag:command-translation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3103395696}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-14T14:07:56.405960+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4850193", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "yujianboisme/qwen2.5-1.5b-darkhorse-code-fine-tuning", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3087467712, "estimatedRequiredGiB": 3.468, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 802490000, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1543714304, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:text-generation", "custom_tag:qwen2.5", "custom_tag:lora", "custom_tag:json", "custom_tag:instruction-following", "custom_tag:chinese", "custom_tag:command-translation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3103395696}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-14T14:07:56.405960+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4850193", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "yujianboisme/qwen2.5-1.5b-darkhorse-code-fine-tuning", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3087467712, "estimatedRequiredGiB": 3.468, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 3103395696, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1543714304, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:text-generation", "custom_tag:qwen2.5", "custom_tag:lora", "custom_tag:json", "custom_tag:instruction-following", "custom_tag:chinese", "custom_tag:command-translation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3103395696}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-14T14:28:45.912561+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4850731", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "yujianboisme/qwen2.5-1.5b-darkhorse-code-fine-tuning", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3087467712, "estimatedRequiredGiB": 3.468, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 3103395696, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1543714304, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:text-generation", "custom_tag:qwen2.5", "custom_tag:lora", "custom_tag:json", "custom_tag:instruction-following", "custom_tag:chinese", "custom_tag:command-translation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3103395696}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-14T14:28:45.912561+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4850731", "taskType": "text-generation", "verifyResult": null}