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

state: generation 10396 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-20 08:31:40 +00:00
parent f92b97244c
commit b2bbd2bec5
8 changed files with 1802 additions and 1803 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": "2026-09-20T08:28:03.640396+00:00", "generatedAt": "2026-09-20T08:31:30.830856+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": "2026-09-20T08:30:29.440155+00:00", "generatedAt": "2026-09-20T08:31:39.083158+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": "2026-09-20T08:30:29.440155+00:00", "catalogUpdatedAt": "2026-09-20T08:31:39.083158+00:00",
"configuredTaskTypes": [ "configuredTaskTypes": [
"text-generation" "text-generation"
], ],
@@ -56,7 +56,7 @@
"time-series-forecasting" "time-series-forecasting"
], ],
"errors": [], "errors": [],
"generatedAt": "2026-09-20T08:30:29.440155+00:00", "generatedAt": "2026-09-20T08:31:39.083158+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": "2026-09-20T08:30:29.440155+00:00", "taskTreeUpdatedAt": "2026-09-20T08:31:39.083158+00:00",
"version": 1 "version": 1
} }

96
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{ {
"generatedAt": "2026-09-20T08:28:03.593425+00:00", "generatedAt": "2026-09-20T08:31:30.745590+00:00",
"lastSyncTime": "2026-09-20T08:28:03.157173+00:00", "lastSyncTime": "2026-09-20T08:31:30.458816+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -2200,27 +2200,27 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Biren_166m|vllm|text-generation": { "Biren_166m|vllm|text-generation": {
"attributableFailureCount": 32, "attributableFailureCount": 33,
"decisionFailureRate": 0.6957, "decisionFailureRate": 0.7021,
"decisionSuccessRate": 0.3043, "decisionSuccessRate": 0.2979,
"decisionTotal": 46, "decisionTotal": 47,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 1, "ambiguous_runtime": 1,
"framework_architecture_unsupported": 25, "framework_architecture_unsupported": 26,
"model_load": 6, "model_load": 6,
"tokenizer_compatibility": 1 "tokenizer_compatibility": 1
}, },
"failureCount": 33, "failureCount": 34,
"failureRate": 0.7021, "failureRate": 0.7083,
"framework": "vllm", "framework": "vllm",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 14, "successCount": 14,
"successRate": 0.2979, "successRate": 0.2917,
"targetGpu": "Biren_166m", "targetGpu": "Biren_166m",
"taskType": "text-generation", "taskType": "text-generation",
"total": 47, "total": 48,
"unresolvedFailureCount": 1 "unresolvedFailureCount": 1
}, },
"Cambricon_mlu-370-x4|unknown|text-generation": { "Cambricon_mlu-370-x4|unknown|text-generation": {
@@ -4225,17 +4225,17 @@
"unresolvedFailureCount": 6404 "unresolvedFailureCount": 6404
}, },
"vllm": { "vllm": {
"attributableFailureCount": 3462, "attributableFailureCount": 3463,
"decisionFailureRate": 0.9793, "decisionFailureRate": 0.9794,
"decisionSuccessRate": 0.0207, "decisionSuccessRate": 0.0206,
"decisionTotal": 3535, "decisionTotal": 3536,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 1427, "ambiguous_runtime": 1427,
"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": 1253, "framework_architecture_unsupported": 1254,
"memory_capacity": 718, "memory_capacity": 718,
"model_load": 197, "model_load": 197,
"platform_infrastructure": 864, "platform_infrastructure": 864,
@@ -4244,14 +4244,14 @@
"tokenizer_compatibility": 406, "tokenizer_compatibility": 406,
"参数/模板问题": 40 "参数/模板问题": 40
}, },
"failureCount": 5793, "failureCount": 5794,
"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": 5866, "total": 5867,
"unresolvedFailureCount": 1467 "unresolvedFailureCount": 1467
}, },
"vllm-mlu": { "vllm-mlu": {
@@ -4364,7 +4364,7 @@
"unresolvedFailureCount": 23 "unresolvedFailureCount": 23
} }
}, },
"generatedAt": "2026-09-20T08:28:03.586846+00:00", "generatedAt": "2026-09-20T08:31:30.738700+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 72, "attributableFailureCount": 72,
@@ -4420,15 +4420,15 @@
"unresolvedFailureCount": 587 "unresolvedFailureCount": 587
}, },
"Biren_166m": { "Biren_166m": {
"attributableFailureCount": 170, "attributableFailureCount": 171,
"decisionFailureRate": 0.8763, "decisionFailureRate": 0.8769,
"decisionSuccessRate": 0.1237, "decisionSuccessRate": 0.1231,
"decisionTotal": 194, "decisionTotal": 195,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 131, "ambiguous_runtime": 131,
"backend_operator": 4, "backend_operator": 4,
"context_length": 10, "context_length": 10,
"framework_architecture_unsupported": 112, "framework_architecture_unsupported": 113,
"memory_capacity": 1, "memory_capacity": 1,
"model_load": 17, "model_load": 17,
"platform_infrastructure": 2, "platform_infrastructure": 2,
@@ -4439,14 +4439,14 @@
"日志缺失": 62, "日志缺失": 62,
"验证失败": 27 "验证失败": 27
}, },
"failureCount": 606, "failureCount": 607,
"failureRate": 0.9619, "failureRate": 0.962,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 2, "platformFailureCount": 2,
"successCount": 24, "successCount": 24,
"successRate": 0.0381, "successRate": 0.038,
"total": 630, "total": 631,
"unresolvedFailureCount": 434 "unresolvedFailureCount": 434
}, },
"Cambricon_mlu-370-x4": { "Cambricon_mlu-370-x4": {
@@ -5572,14 +5572,14 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Biren_166m|vllm|text-generation|qwen3_5_moe|compressed-tensors": { "Biren_166m|vllm|text-generation|qwen3_5_moe|compressed-tensors": {
"attributableFailureCount": 2, "attributableFailureCount": 3,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 2, "decisionTotal": 3,
"failureBreakdown": { "failureBreakdown": {
"framework_architecture_unsupported": 2 "framework_architecture_unsupported": 3
}, },
"failureCount": 2, "failureCount": 3,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"modelType": "qwen3_5_moe", "modelType": "qwen3_5_moe",
@@ -5591,7 +5591,7 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Biren_166m", "targetGpu": "Biren_166m",
"taskType": "text-generation", "taskType": "text-generation",
"total": 2, "total": 3,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Biren_166m|vllm|text-generation|qwen3_5_moe|none": { "Biren_166m|vllm|text-generation|qwen3_5_moe|none": {
@@ -11741,14 +11741,14 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Biren_166m|vllm|text-generation|qwen3_5_moe|compressed-tensors|34": { "Biren_166m|vllm|text-generation|qwen3_5_moe|compressed-tensors|34": {
"attributableFailureCount": 2, "attributableFailureCount": 3,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 2, "decisionTotal": 3,
"failureBreakdown": { "failureBreakdown": {
"framework_architecture_unsupported": 2 "framework_architecture_unsupported": 3
}, },
"failureCount": 2, "failureCount": 3,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"loadSizeLog2Bucket": 34, "loadSizeLog2Bucket": 34,
@@ -11761,7 +11761,7 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Biren_166m", "targetGpu": "Biren_166m",
"taskType": "text-generation", "taskType": "text-generation",
"total": 2, "total": 3,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Biren_166m|vllm|text-generation|qwen3_5_moe|none|34": { "Biren_166m|vllm|text-generation|qwen3_5_moe|none|34": {
@@ -18252,20 +18252,20 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 15768, "terminalRecords": 15769,
"totalRecords": 15871, "totalRecords": 15872,
"totals": { "totals": {
"attributableFailureCount": 5706, "attributableFailureCount": 5707,
"decisionFailureRate": 0.8614, "decisionFailureRate": 0.8614,
"decisionSuccessRate": 0.1386, "decisionSuccessRate": 0.1386,
"decisionTotal": 6624, "decisionTotal": 6625,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 3720, "ambiguous_runtime": 3720,
"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": 1962, "framework_architecture_unsupported": 1963,
"memory_capacity": 1181, "memory_capacity": 1181,
"model_load": 474, "model_load": 474,
"platform_infrastructure": 922, "platform_infrastructure": 922,
@@ -18276,14 +18276,14 @@
"日志缺失": 719, "日志缺失": 719,
"验证失败": 673 "验证失败": 673
}, },
"failureCount": 14850, "failureCount": 14851,
"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": 15768, "total": 15769,
"unresolvedFailureCount": 8222 "unresolvedFailureCount": 8222
}, },
"warnings": [ "warnings": [
@@ -18327,13 +18327,13 @@
"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": 15871, "summarizedRecords": 15872,
"version": 1 "version": 1
} }

1520
.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": "bc0c7df95e03d9934f57374d2e0163cdc2de4a67af2f105dea4ace7aed2b04e4", ".modelhub_state/architecture_compatibility_blacklist.json": "cf93ee85d4ffc1fa1c364e1e1553b7f122b0d8931ce0fa51758c97d75bdbf209",
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
".modelhub_state/market_intelligence.json": "edbd572f24615415e224fe981898f8b77c329a1468ab13254f7fc01ab6764363", ".modelhub_state/market_intelligence.json": "4c768eafd32740cc8388509f6518722a882b6dc7d004ff0f85b07db6e4dcba56",
".modelhub_state/official_capabilities.json": "a22b513b4996b99e132db02775ed6dee2859a4efb17ad5bcf0f9ea28c481c942", ".modelhub_state/official_capabilities.json": "1bfd8d992dd472b5f2843c103778a9d01d8a8b5ed07a885aed95037b8e8a2a51",
".modelhub_state/outcome_checkpoint.json": "beb28f8dd7d0a36b6d59614978858fb06b1dc3c2f63674c614638f53bfdc51b7", ".modelhub_state/outcome_checkpoint.json": "6551ee77199c268373459a0148df0c58800634baf386f244133d7a5182e406eb",
".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": "effdb87a05cf1902eb3788e80e6919ae802bc10eae7bba40662cfaaccdf8a04f", ".modelhub_state/recovery_active_tasks.jsonl": "ba993a4b636dd0a72eb29c2d4550942d1c146592c0c2807207d03b2880355bbb",
".modelhub_state/recovery_intents.jsonl": "102c6c826eaa2c94057954fbb6136382923e134b227aaaa6ff0cb1a0703a3252", ".modelhub_state/recovery_intents.jsonl": "28daecc38b09ed64f4e925391c84a26d136bb59f57e3465381b3888c0130bf73",
".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": "3dd9f8db02e73b4a64ca29d0edc54f083ca6b2a2eac434fbcf8d9220f8370d40" "outcomes/submissions.jsonl": "1b746b58ecb3484781aa0fc1343d4f92801f7680a08479fca6a964eb74ebe328"
}, },
"generation": 10395, "generation": 10396,
"phase": "cycle", "phase": "cycle",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-09-20T08:30:29.829965+00:00", "updatedAt": "2026-09-20T08:31:39.978476+00:00",
"writerId": "fc715c06e24c4db2ae3e425e435db996" "writerId": "fc715c06e24c4db2ae3e425e435db996"
} }

1
outcomes/submissions.jsonl
View File

@@ -184,7 +184,6 @@
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-10T15:40:28.508808+00:00", "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "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": "2026-09-10T07:33:41.787375+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4756078", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-10T15:40:28.508808+00:00", "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "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": "2026-09-10T07:33:41.787375+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4756078", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T15:56:47.546297+00:00", "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "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": "2026-09-10T07:50:25.385741+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4756398", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T15:56:47.546297+00:00", "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "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": "2026-09-10T07:50:25.385741+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4756398", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T17:58:58.347463+00:00", "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "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": "2026-09-10T09:52:16.471862+00:00", "targetGpu": "MetaX_c-500", "taskId": "4758203", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T17:58:58.347463+00:00", "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "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": "2026-09-10T09:52:16.471862+00:00", "targetGpu": "MetaX_c-500", "taskId": "4758203", "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": "2026-09-10T22:47:57.504483+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}