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

state: generation 10390 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-20 08:24:46 +00:00
parent 7d9acaf594
commit 9eda563b91
8 changed files with 1799 additions and 1800 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -1783,7 +1783,7 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-09-20T08:10:45.961097+00:00", "generatedAt": "2026-09-20T08:24:40.026968+00:00",
"summary": { "summary": {
"activeBlockCount": 86, "activeBlockCount": 86,
"byGpuFramework": { "byGpuFramework": {

2
.modelhub_state/market_intelligence.json
View File

@@ -416,7 +416,7 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-09-20T08:23:17.974826+00:00", "generatedAt": "2026-09-20T08:24:45.926149+00:00",
"gpuStats": { "gpuStats": {
"Ascend_910-b3": { "Ascend_910-b3": {
"available": true, "available": true,

6
.modelhub_state/official_capabilities.json
View File

@@ -1,5 +1,5 @@
{ {
"catalogUpdatedAt": "2026-09-20T08:23:17.974826+00:00", "catalogUpdatedAt": "2026-09-20T08:24:45.926149+00:00",
"configuredTaskTypes": [ "configuredTaskTypes": [
"text-generation" "text-generation"
], ],
@@ -56,7 +56,7 @@
"time-series-forecasting" "time-series-forecasting"
], ],
"errors": [], "errors": [],
"generatedAt": "2026-09-20T08:23:38.733100+00:00", "generatedAt": "2026-09-20T08:24:45.926149+00:00",
"gpuCatalog": { "gpuCatalog": {
"Ascend_910-b3": { "Ascend_910-b3": {
"canVerify": true, "canVerify": true,
@@ -6473,6 +6473,6 @@
"updateTime": "2025-12-22 08:59:53" "updateTime": "2025-12-22 08:59:53"
} }
], ],
"taskTreeUpdatedAt": "2026-09-20T08:23:17.974826+00:00", "taskTreeUpdatedAt": "2026-09-20T08:24:45.926149+00:00",
"version": 1 "version": 1
} }

88
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{ {
"generatedAt": "2026-09-20T07:49:59.037684+00:00", "generatedAt": "2026-09-20T08:24:39.967208+00:00",
"lastSyncTime": "2026-09-20T07:49:58.677579+00:00", "lastSyncTime": "2026-09-20T08:24:39.658601+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -2200,26 +2200,26 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Biren_166m|vllm|text-generation": { "Biren_166m|vllm|text-generation": {
"attributableFailureCount": 31, "attributableFailureCount": 32,
"decisionFailureRate": 0.6889, "decisionFailureRate": 0.6957,
"decisionSuccessRate": 0.3111, "decisionSuccessRate": 0.3043,
"decisionTotal": 45, "decisionTotal": 46,
"failureBreakdown": { "failureBreakdown": {
"framework_architecture_unsupported": 24, "framework_architecture_unsupported": 25,
"model_load": 6, "model_load": 6,
"tokenizer_compatibility": 1 "tokenizer_compatibility": 1
}, },
"failureCount": 31, "failureCount": 32,
"failureRate": 0.6889, "failureRate": 0.6957,
"framework": "vllm", "framework": "vllm",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 14, "successCount": 14,
"successRate": 0.3111, "successRate": 0.3043,
"targetGpu": "Biren_166m", "targetGpu": "Biren_166m",
"taskType": "text-generation", "taskType": "text-generation",
"total": 45, "total": 46,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Cambricon_mlu-370-x4|unknown|text-generation": { "Cambricon_mlu-370-x4|unknown|text-generation": {
@@ -4224,17 +4224,17 @@
"unresolvedFailureCount": 6404 "unresolvedFailureCount": 6404
}, },
"vllm": { "vllm": {
"attributableFailureCount": 3461, "attributableFailureCount": 3462,
"decisionFailureRate": 0.9793, "decisionFailureRate": 0.9793,
"decisionSuccessRate": 0.0207, "decisionSuccessRate": 0.0207,
"decisionTotal": 3534, "decisionTotal": 3535,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 1426, "ambiguous_runtime": 1426,
"architecture_compatibility": 112, "architecture_compatibility": 112,
"attention_backend": 1, "attention_backend": 1,
"backend_operator": 84, "backend_operator": 84,
"context_length": 161, "context_length": 161,
"framework_architecture_unsupported": 1252, "framework_architecture_unsupported": 1253,
"memory_capacity": 718, "memory_capacity": 718,
"model_load": 197, "model_load": 197,
"platform_infrastructure": 864, "platform_infrastructure": 864,
@@ -4243,14 +4243,14 @@
"tokenizer_compatibility": 406, "tokenizer_compatibility": 406,
"参数/模板问题": 40 "参数/模板问题": 40
}, },
"failureCount": 5791, "failureCount": 5792,
"failureRate": 0.9876, "failureRate": 0.9876,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 864, "platformFailureCount": 864,
"successCount": 73, "successCount": 73,
"successRate": 0.0124, "successRate": 0.0124,
"total": 5864, "total": 5865,
"unresolvedFailureCount": 1466 "unresolvedFailureCount": 1466
}, },
"vllm-mlu": { "vllm-mlu": {
@@ -4363,7 +4363,7 @@
"unresolvedFailureCount": 23 "unresolvedFailureCount": 23
} }
}, },
"generatedAt": "2026-09-20T07:49:59.031122+00:00", "generatedAt": "2026-09-20T08:24:39.960094+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 72, "attributableFailureCount": 72,
@@ -4419,15 +4419,15 @@
"unresolvedFailureCount": 587 "unresolvedFailureCount": 587
}, },
"Biren_166m": { "Biren_166m": {
"attributableFailureCount": 169, "attributableFailureCount": 170,
"decisionFailureRate": 0.8756, "decisionFailureRate": 0.8763,
"decisionSuccessRate": 0.1244, "decisionSuccessRate": 0.1237,
"decisionTotal": 193, "decisionTotal": 194,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 130, "ambiguous_runtime": 130,
"backend_operator": 4, "backend_operator": 4,
"context_length": 10, "context_length": 10,
"framework_architecture_unsupported": 111, "framework_architecture_unsupported": 112,
"memory_capacity": 1, "memory_capacity": 1,
"model_load": 17, "model_load": 17,
"platform_infrastructure": 2, "platform_infrastructure": 2,
@@ -4438,14 +4438,14 @@
"日志缺失": 62, "日志缺失": 62,
"验证失败": 27 "验证失败": 27
}, },
"failureCount": 604, "failureCount": 605,
"failureRate": 0.9618, "failureRate": 0.9618,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 2, "platformFailureCount": 2,
"successCount": 24, "successCount": 24,
"successRate": 0.0382, "successRate": 0.0382,
"total": 628, "total": 629,
"unresolvedFailureCount": 433 "unresolvedFailureCount": 433
}, },
"Cambricon_mlu-370-x4": { "Cambricon_mlu-370-x4": {
@@ -5732,14 +5732,14 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Biren_166m|vllm|text-generation|qwen3_5|none": { "Biren_166m|vllm|text-generation|qwen3_5|none": {
"attributableFailureCount": 4, "attributableFailureCount": 5,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 4, "decisionTotal": 5,
"failureBreakdown": { "failureBreakdown": {
"framework_architecture_unsupported": 4 "framework_architecture_unsupported": 5
}, },
"failureCount": 4, "failureCount": 5,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"modelType": "qwen3_5", "modelType": "qwen3_5",
@@ -5751,7 +5751,7 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Biren_166m", "targetGpu": "Biren_166m",
"taskType": "text-generation", "taskType": "text-generation",
"total": 4, "total": 5,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Biren_166m|vllm|text-generation|qwen3|none": { "Biren_166m|vllm|text-generation|qwen3|none": {
@@ -11981,14 +11981,14 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Biren_166m|vllm|text-generation|qwen3_5|none|33": { "Biren_166m|vllm|text-generation|qwen3_5|none|33": {
"attributableFailureCount": 1, "attributableFailureCount": 2,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 1, "decisionTotal": 2,
"failureBreakdown": { "failureBreakdown": {
"framework_architecture_unsupported": 1 "framework_architecture_unsupported": 2
}, },
"failureCount": 1, "failureCount": 2,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"loadSizeLog2Bucket": 33, "loadSizeLog2Bucket": 33,
@@ -12001,7 +12001,7 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Biren_166m", "targetGpu": "Biren_166m",
"taskType": "text-generation", "taskType": "text-generation",
"total": 1, "total": 2,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Biren_166m|vllm|text-generation|qwen3_5|none|34": { "Biren_166m|vllm|text-generation|qwen3_5|none|34": {
@@ -18204,20 +18204,20 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 15766, "terminalRecords": 15767,
"totalRecords": 15869, "totalRecords": 15870,
"totals": { "totals": {
"attributableFailureCount": 5705, "attributableFailureCount": 5706,
"decisionFailureRate": 0.8614, "decisionFailureRate": 0.8614,
"decisionSuccessRate": 0.1386, "decisionSuccessRate": 0.1386,
"decisionTotal": 6623, "decisionTotal": 6624,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 3719, "ambiguous_runtime": 3719,
"architecture_compatibility": 212, "architecture_compatibility": 212,
"attention_backend": 1, "attention_backend": 1,
"backend_operator": 101, "backend_operator": 101,
"context_length": 318, "context_length": 318,
"framework_architecture_unsupported": 1961, "framework_architecture_unsupported": 1962,
"memory_capacity": 1181, "memory_capacity": 1181,
"model_load": 474, "model_load": 474,
"platform_infrastructure": 922, "platform_infrastructure": 922,
@@ -18228,14 +18228,14 @@
"日志缺失": 719, "日志缺失": 719,
"验证失败": 673 "验证失败": 673
}, },
"failureCount": 14848, "failureCount": 14849,
"failureRate": 0.9418, "failureRate": 0.9418,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 922, "platformFailureCount": 922,
"successCount": 918, "successCount": 918,
"successRate": 0.0582, "successRate": 0.0582,
"total": 15766, "total": 15767,
"unresolvedFailureCount": 8221 "unresolvedFailureCount": 8221
}, },
"warnings": [ "warnings": [
@@ -18279,13 +18279,13 @@
"组合 Ascend_910-b3|vllm_tokenizer_patch|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_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Cambricon_mlu-370-x4|unknown|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Cambricon_mlu-370-x4|unknown|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Ascend_910-b4|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-b4|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Cambricon_mlu-370-x8|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Cambricon_mlu-370-x8|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Cambricon_mlu-370-x8|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"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。", "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。",
"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 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 Cambricon_mlu-370-x8|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。"
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 15869, "summarizedRecords": 15870,
"version": 1 "version": 1
} }

1522
.modelhub_state/recovery_active_tasks.jsonl
View File

File diff suppressed because it is too large Load Diff

1960
.modelhub_state/recovery_intents.jsonl
View File

File diff suppressed because it is too large Load Diff

18
manifest.json
View File

@@ -1,24 +1,24 @@
{ {
"agentVersion": "2026.09.20.2", "agentVersion": "2026.09.20.2",
"checksums": { "checksums": {
".modelhub_state/architecture_compatibility_blacklist.json": "93ea8e311d89e4e93ccb1de8dc75039dbee1f48bed4607cd2cb3803661404e44", ".modelhub_state/architecture_compatibility_blacklist.json": "184f00df71e3997cb06666060b81f7e025075bbfbf56ce0fe4dd30c560e81761",
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
".modelhub_state/market_intelligence.json": "7e7ed4db5a598f6318983e51fb1c149b09c7b3fdbf9b546b1b8ba0736a6d3833", ".modelhub_state/market_intelligence.json": "dc103cf50417aa35cf75df1cb816e785096a38e34dc0ca555f8a849b0665c0f8",
".modelhub_state/official_capabilities.json": "eb3c47bc829c632e42a9a3e8a82bd7ad4096591cf70bc03a6240e33f3a5f5410", ".modelhub_state/official_capabilities.json": "5eac4455677d95b5e5642a2b268a9ab9b43e1177e2bff32f26f90506d7f35f61",
".modelhub_state/outcome_checkpoint.json": "0e5777c68f072bf9a227c135f9e13b97229d29927d9b3259d403e50c6ded6bd1", ".modelhub_state/outcome_checkpoint.json": "4ba439a541e54d02e1e2b59a3726ead952329d6ebdceeee7b3042f378b13aeb0",
".modelhub_state/queue_cleanup_latest.json": "a43deb60b6f751b76576986b5c89b51a2b8d469239d82ff9136f564b25b03b2c", ".modelhub_state/queue_cleanup_latest.json": "a43deb60b6f751b76576986b5c89b51a2b8d469239d82ff9136f564b25b03b2c",
".modelhub_state/recent_outcomes.jsonl": "e4ec7fe7a933ada1495dda90138340a94157c38bdea2cbc2d2155d9b305ba72e", ".modelhub_state/recent_outcomes.jsonl": "e4ec7fe7a933ada1495dda90138340a94157c38bdea2cbc2d2155d9b305ba72e",
".modelhub_state/recovery_active_tasks.jsonl": "788fda66aa868fc6fa4ec4e0d095af1824329e7b04b6ee479023e7e394b1dae1", ".modelhub_state/recovery_active_tasks.jsonl": "5b454eefaf2aa22236e4194b7bad866fe160e61c4a30ec04f6b293b30e25835e",
".modelhub_state/recovery_intents.jsonl": "259a0410235a3ee263ac79107e87914d6197a0d69334e1e35fd1428372023e9b", ".modelhub_state/recovery_intents.jsonl": "ef238b1c6c2a55dadd072c6915ffa4a10f179da8ea29319e6268f1ab69be472b",
".modelhub_state/routing_intelligence.json": "010a51428f05fdbd5668d304922f379c5690533e678aece411bee97754fb4c9a", ".modelhub_state/routing_intelligence.json": "010a51428f05fdbd5668d304922f379c5690533e678aece411bee97754fb4c9a",
".modelhub_state/submission_exclusions.jsonl": "221be895a524330815b3c5124450b33c94b5f1e68169030c73684bf675d06ec7", ".modelhub_state/submission_exclusions.jsonl": "221be895a524330815b3c5124450b33c94b5f1e68169030c73684bf675d06ec7",
".modelhub_state/worker_crashes.jsonl": "a494412048eca6dce83e7284303a6b4b56a445c1274ac201ab8723c739a14f23", ".modelhub_state/worker_crashes.jsonl": "a494412048eca6dce83e7284303a6b4b56a445c1274ac201ab8723c739a14f23",
"ledger/submissions.jsonl": "0d42c01ce8e175a145f6185042c3344c7a25ef4025964e2ebcbc5c929309efc3", "ledger/submissions.jsonl": "0d42c01ce8e175a145f6185042c3344c7a25ef4025964e2ebcbc5c929309efc3",
"outcomes/submissions.jsonl": "a906658ca37ee7c7ac524c605bdd4e0118dbdd037d05693f61b425a92fbe66ab" "outcomes/submissions.jsonl": "5c3051c3a786ebfbb6f2b4a48ca0b2543d49ef9919890ff94d16b9d639e15f80"
}, },
"generation": 10389, "generation": 10390,
"phase": "cycle", "phase": "cycle",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-09-20T08:23:38.945455+00:00", "updatedAt": "2026-09-20T08:24:46.834694+00:00",
"writerId": "fc715c06e24c4db2ae3e425e435db996" "writerId": "fc715c06e24c4db2ae3e425e435db996"
} }

1
outcomes/submissions.jsonl
View File

@@ -187,7 +187,6 @@
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T21:33:23.930709+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26057989872, "estimatedRequiredGiB": 29.158, "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": 26090095180, "modelscopeLicense": "apache-2.0", "modelscopeParams": 21416999792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:fp8", "custom_tag:mixed-precision", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26090095180}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T13:27:23.401229+00:00", "targetGpu": "Biren_166m", "taskId": "4760703", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T21:33:23.930709+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26057989872, "estimatedRequiredGiB": 29.158, "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": 26090095180, "modelscopeLicense": "apache-2.0", "modelscopeParams": 21416999792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:fp8", "custom_tag:mixed-precision", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26090095180}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T13:27:23.401229+00:00", "targetGpu": "Biren_166m", "taskId": "4760703", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T21:33:23.930689+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 38136526544, "estimatedRequiredGiB": 42.65, "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": 38162746086, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107181936, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:fp8", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 38162746086}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T13:27:23.406185+00:00", "targetGpu": "Biren_166m", "taskId": "4760702", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T21:33:23.930689+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 38136526544, "estimatedRequiredGiB": 42.65, "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": 38162746086, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107181936, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:fp8", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 38162746086}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T13:27:23.406185+00:00", "targetGpu": "Biren_166m", "taskId": "4760702", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T21:33:23.930703+00:00", "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730844445, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:reasoning", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730844445}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T13:27:23.410963+00:00", "targetGpu": "Biren_166m", "taskId": "4760705", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T21:33:23.930703+00:00", "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730844445, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:reasoning", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730844445}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T13:27:23.410963+00:00", "targetGpu": "Biren_166m", "taskId": "4760705", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T21:33:23.930655+00:00", "modelId": "BAAI/AREX-Turbo", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9078620368, "estimatedRequiredGiB": 10.18, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9109259594, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4539265536, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:deep-research", "custom_tag:reasoning", "custom_tag:tool-use", "custom_tag:long-context", "custom_tag:qwen3.5", "custom_tag:dense"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9109259594}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T13:27:23.409305+00:00", "targetGpu": "Biren_166m", "taskId": "4760704", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T22:47:57.504483+00:00", "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730844445, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:reasoning", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730844445}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T14:46:30.893195+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4761530", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T22:47:57.504483+00:00", "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730844445, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:reasoning", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730844445}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T14:46:30.893195+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4761530", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T22:47:57.504463+00:00", "modelId": "BAAI/AREX-Turbo", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9078620368, "estimatedRequiredGiB": 10.18, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9109259594, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4539265536, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:deep-research", "custom_tag:reasoning", "custom_tag:tool-use", "custom_tag:long-context", "custom_tag:qwen3.5", "custom_tag:dense"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9109259594}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T14:46:30.895806+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4761531", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T22:47:57.504463+00:00", "modelId": "BAAI/AREX-Turbo", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9078620368, "estimatedRequiredGiB": 10.18, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9109259594, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4539265536, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:deep-research", "custom_tag:reasoning", "custom_tag:tool-use", "custom_tag:long-context", "custom_tag:qwen3.5", "custom_tag:dense"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9109259594}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T14:46:30.895806+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4761531", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-10T23:20:13.106498+00:00", "modelId": "webAI-Official/TwIL-LM3", "modelProfile": {"architectures": ["SmolLM3ForCausalLM"], "configFingerprint": "e4ab8f6cadfae4845d02aa9c1f89de5907e1f311ae817b1e8e370b501bd7f2e9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3275575456, "estimatedRequiredGiB": 24.879, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "smollm3", "modelscopeFileSize": 22261451378, "modelscopeLicense": "other", "modelscopeParams": 3075098624, "modelscopeTags": ["license:other", "model_type:smollm3", "library:pytorch", "library:transformer", "library:lora", "library:safetensors", "library:gguf", "task:text-generation", "custom_tag:formal-logic", "custom_tag:reasoning", "custom_tag:lora", "custom_tag:model-merging", "custom_tag:wise-ft", "custom_tag:reinforcement-learning", "custom_tag:grpo", "custom_tag:smollm3", "custom_tag:twil-lm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22261451381}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T15:13:26.242352+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4761809", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-10T23:20:13.106498+00:00", "modelId": "webAI-Official/TwIL-LM3", "modelProfile": {"architectures": ["SmolLM3ForCausalLM"], "configFingerprint": "e4ab8f6cadfae4845d02aa9c1f89de5907e1f311ae817b1e8e370b501bd7f2e9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3275575456, "estimatedRequiredGiB": 24.879, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "smollm3", "modelscopeFileSize": 22261451378, "modelscopeLicense": "other", "modelscopeParams": 3075098624, "modelscopeTags": ["license:other", "model_type:smollm3", "library:pytorch", "library:transformer", "library:lora", "library:safetensors", "library:gguf", "task:text-generation", "custom_tag:formal-logic", "custom_tag:reasoning", "custom_tag:lora", "custom_tag:model-merging", "custom_tag:wise-ft", "custom_tag:reinforcement-learning", "custom_tag:grpo", "custom_tag:smollm3", "custom_tag:twil-lm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22261451381}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T15:13:26.242352+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4761809", "taskType": "text-generation", "verifyResult": null}