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

state: generation 10944 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-20 22:24:13 +00:00
parent 305f4a6f20
commit c999e50ec5
10 changed files with 1964 additions and 1902 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -806,6 +806,25 @@
"targetGpu": "Cambricon_mlu-370-x8", "targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation" "taskType": "text-generation"
}, },
"cambricon_mlu-370-x8|vllm|text-generation|model_type:qwen3": {
"architectureSignature": "model_type:qwen3",
"architectures": [],
"evidenceCount": 1,
"expiresAt": "2026-10-20T04:02:52.200512+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-20T04:02:52.200512+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "qwen3",
"sourceModelIds": [
"whcl412/mlx-LycheeAI-coder-1.7b"
],
"sourceTaskIds": [
"4970447"
],
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation"
},
"cambricon_mlu-370-x8|vllm|text-generation|model_type:qwen3_5": { "cambricon_mlu-370-x8|vllm|text-generation|model_type:qwen3_5": {
"architectureSignature": "model_type:qwen3_5", "architectureSignature": "model_type:qwen3_5",
"architectures": [], "architectures": [],
@@ -2283,16 +2302,16 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-09-20T22:20:31.840646+00:00", "generatedAt": "2026-09-20T22:24:01.675690+00:00",
"summary": { "summary": {
"activeBlockCount": 112, "activeBlockCount": 113,
"byGpuFramework": { "byGpuFramework": {
"Ascend_910-b3|vllm": 11, "Ascend_910-b3|vllm": 11,
"Ascend_910-b3|vllm_tokenizer_patch": 4, "Ascend_910-b3|vllm_tokenizer_patch": 4,
"Ascend_910-b4|vllm": 12, "Ascend_910-b4|vllm": 12,
"Ascend_910-b4|vllm_tokenizer_patch": 3, "Ascend_910-b4|vllm_tokenizer_patch": 3,
"Biren_166m|vllm": 3, "Biren_166m|vllm": 3,
"Cambricon_mlu-370-x8|vllm": 6, "Cambricon_mlu-370-x8|vllm": 7,
"Cambricon_mlu-370-x8|vllm-mlu": 5, "Cambricon_mlu-370-x8|vllm-mlu": 5,
"Iluvatar_bi-150|transformers": 4, "Iluvatar_bi-150|transformers": 4,
"Iluvatar_bi-150|vllm": 7, "Iluvatar_bi-150|vllm": 7,

2
.modelhub_state/market_intelligence.json
View File

@@ -425,7 +425,7 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-09-20T22:23:00.159965+00:00", "generatedAt": "2026-09-20T22:24:12.597647+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": "2026-09-20T22:23:00.159965+00:00", "catalogUpdatedAt": "2026-09-20T22:24:12.597647+00:00",
"configuredTaskTypes": [ "configuredTaskTypes": [
"text-generation" "text-generation"
], ],
@@ -56,7 +56,7 @@
"time-series-forecasting" "time-series-forecasting"
], ],
"errors": [], "errors": [],
"generatedAt": "2026-09-20T22:23:00.159965+00:00", "generatedAt": "2026-09-20T22:24:12.597647+00:00",
"gpuCatalog": { "gpuCatalog": {
"Ascend_910-b3": { "Ascend_910-b3": {
"canVerify": true, "canVerify": true,
@@ -6455,6 +6455,6 @@
"updateTime": "2025-12-22 08:59:53" "updateTime": "2025-12-22 08:59:53"
} }
], ],
"taskTreeUpdatedAt": "2026-09-20T22:23:00.159965+00:00", "taskTreeUpdatedAt": "2026-09-20T22:24:12.597647+00:00",
"version": 1 "version": 1
} }

191
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{ {
"generatedAt": "2026-09-20T22:20:31.772739+00:00", "generatedAt": "2026-09-20T22:24:01.602124+00:00",
"lastSyncTime": "2026-09-20T22:20:31.465723+00:00", "lastSyncTime": "2026-09-20T22:24:01.251307+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -810,6 +810,25 @@
"targetGpu": "Cambricon_mlu-370-x8", "targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation" "taskType": "text-generation"
}, },
"cambricon_mlu-370-x8|vllm|text-generation|model_type:qwen3": {
"architectureSignature": "model_type:qwen3",
"architectures": [],
"evidenceCount": 1,
"expiresAt": "2026-10-20T04:02:52.200512+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-20T04:02:52.200512+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "qwen3",
"sourceModelIds": [
"whcl412/mlx-LycheeAI-coder-1.7b"
],
"sourceTaskIds": [
"4970447"
],
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation"
},
"cambricon_mlu-370-x8|vllm|text-generation|model_type:qwen3_5": { "cambricon_mlu-370-x8|vllm|text-generation|model_type:qwen3_5": {
"architectureSignature": "model_type:qwen3_5", "architectureSignature": "model_type:qwen3_5",
"architectures": [], "architectures": [],
@@ -2288,14 +2307,14 @@
} }
}, },
"architectureCompatibilitySummary": { "architectureCompatibilitySummary": {
"activeBlockCount": 112, "activeBlockCount": 113,
"byGpuFramework": { "byGpuFramework": {
"Ascend_910-b3|vllm": 11, "Ascend_910-b3|vllm": 11,
"Ascend_910-b3|vllm_tokenizer_patch": 4, "Ascend_910-b3|vllm_tokenizer_patch": 4,
"Ascend_910-b4|vllm": 12, "Ascend_910-b4|vllm": 12,
"Ascend_910-b4|vllm_tokenizer_patch": 3, "Ascend_910-b4|vllm_tokenizer_patch": 3,
"Biren_166m|vllm": 3, "Biren_166m|vllm": 3,
"Cambricon_mlu-370-x8|vllm": 6, "Cambricon_mlu-370-x8|vllm": 7,
"Cambricon_mlu-370-x8|vllm-mlu": 5, "Cambricon_mlu-370-x8|vllm-mlu": 5,
"Iluvatar_bi-150|transformers": 4, "Iluvatar_bi-150|transformers": 4,
"Iluvatar_bi-150|vllm": 7, "Iluvatar_bi-150|vllm": 7,
@@ -2925,16 +2944,16 @@
"unresolvedFailureCount": 38 "unresolvedFailureCount": 38
}, },
"Cambricon_mlu-370-x8|vllm|text-generation": { "Cambricon_mlu-370-x8|vllm|text-generation": {
"attributableFailureCount": 9, "attributableFailureCount": 10,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 9, "decisionTotal": 10,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 2, "ambiguous_runtime": 2,
"framework_architecture_unsupported": 9, "framework_architecture_unsupported": 10,
"参数/模板问题": 10 "参数/模板问题": 10
}, },
"failureCount": 21, "failureCount": 22,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"pendingCount": 0, "pendingCount": 0,
@@ -2944,7 +2963,7 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8", "targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation", "taskType": "text-generation",
"total": 21, "total": 22,
"unresolvedFailureCount": 12 "unresolvedFailureCount": 12
}, },
"Iluvatar_bi-100|transformers|text-generation": { "Iluvatar_bi-100|transformers|text-generation": {
@@ -4871,17 +4890,17 @@
"unresolvedFailureCount": 6406 "unresolvedFailureCount": 6406
}, },
"vllm": { "vllm": {
"attributableFailureCount": 3494, "attributableFailureCount": 3495,
"decisionFailureRate": 0.9768, "decisionFailureRate": 0.9768,
"decisionSuccessRate": 0.0232, "decisionSuccessRate": 0.0232,
"decisionTotal": 3577, "decisionTotal": 3578,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 1443, "ambiguous_runtime": 1443,
"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": 1273, "framework_architecture_unsupported": 1274,
"memory_capacity": 720, "memory_capacity": 720,
"model_load": 201, "model_load": 201,
"platform_infrastructure": 864, "platform_infrastructure": 864,
@@ -4890,14 +4909,14 @@
"tokenizer_compatibility": 409, "tokenizer_compatibility": 409,
"参数/模板问题": 40 "参数/模板问题": 40
}, },
"failureCount": 5841, "failureCount": 5842,
"failureRate": 0.986, "failureRate": 0.986,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 864, "platformFailureCount": 864,
"successCount": 83, "successCount": 83,
"successRate": 0.014, "successRate": 0.014,
"total": 5924, "total": 5925,
"unresolvedFailureCount": 1483 "unresolvedFailureCount": 1483
}, },
"vllm-customized": { "vllm-customized": {
@@ -5034,7 +5053,7 @@
"unresolvedFailureCount": 37 "unresolvedFailureCount": 37
} }
}, },
"generatedAt": "2026-09-20T22:20:31.763393+00:00", "generatedAt": "2026-09-20T22:24:01.593001+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 81, "attributableFailureCount": 81,
@@ -5149,27 +5168,27 @@
"unresolvedFailureCount": 763 "unresolvedFailureCount": 763
}, },
"Cambricon_mlu-370-x8": { "Cambricon_mlu-370-x8": {
"attributableFailureCount": 35, "attributableFailureCount": 36,
"decisionFailureRate": 0.7143, "decisionFailureRate": 0.72,
"decisionSuccessRate": 0.2857, "decisionSuccessRate": 0.28,
"decisionTotal": 49, "decisionTotal": 50,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 78, "ambiguous_runtime": 78,
"framework_architecture_unsupported": 29, "framework_architecture_unsupported": 30,
"memory_capacity": 3, "memory_capacity": 3,
"model_load": 1, "model_load": 1,
"tokenizer_compatibility": 2, "tokenizer_compatibility": 2,
"参数/模板问题": 24, "参数/模板问题": 24,
"验证失败": 22 "验证失败": 22
}, },
"failureCount": 159, "failureCount": 160,
"failureRate": 0.9191, "failureRate": 0.9195,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 14, "successCount": 14,
"successRate": 0.0809, "successRate": 0.0805,
"total": 173, "total": 174,
"unresolvedFailureCount": 124 "unresolvedFailureCount": 124
}, },
"Iluvatar_bi-100": { "Iluvatar_bi-100": {
@@ -7969,6 +7988,29 @@
"total": 2, "total": 2,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Cambricon_mlu-370-x8|vllm|text-generation|qwen3|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "qwen3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm|text-generation|spark2_5|fp8": { "Cambricon_mlu-370-x8|vllm|text-generation|spark2_5|fp8": {
"attributableFailureCount": 1, "attributableFailureCount": 1,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
@@ -13179,21 +13221,21 @@
"unresolvedFailureCount": 4 "unresolvedFailureCount": 4
}, },
"Cambricon_mlu-370-x8|vllm|text-generation": { "Cambricon_mlu-370-x8|vllm|text-generation": {
"attributableFailureCount": 6, "attributableFailureCount": 7,
"consecutiveFailures": 6, "consecutiveFailures": 7,
"consecutivePlatformFailures": 0, "consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 6, "decisionTotal": 7,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 2, "ambiguous_runtime": 2,
"framework_architecture_unsupported": 6 "framework_architecture_unsupported": 7
}, },
"failureCount": 8, "failureCount": 9,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-20T17:09:45.266141+00:00", "lastTerminalAt": "2026-09-20T22:24:01.251292+00:00",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
@@ -13201,7 +13243,7 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8", "targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation", "taskType": "text-generation",
"total": 8, "total": 9,
"unresolvedFailureCount": 2 "unresolvedFailureCount": 2
}, },
"Iluvatar_bi-150|transformers|text-generation": { "Iluvatar_bi-150|transformers|text-generation": {
@@ -13341,18 +13383,18 @@
"unresolvedFailureCount": 1 "unresolvedFailureCount": 1
}, },
"Iluvatar_mrv-100|unknown|text-generation": { "Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 7, "attributableFailureCount": 6,
"consecutiveFailures": 1, "consecutiveFailures": 1,
"consecutivePlatformFailures": 0, "consecutivePlatformFailures": 0,
"decisionFailureRate": 0.5385, "decisionFailureRate": 0.5,
"decisionSuccessRate": 0.4615, "decisionSuccessRate": 0.5,
"decisionTotal": 13, "decisionTotal": 12,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 1, "ambiguous_runtime": 1,
"framework_architecture_unsupported": 7 "framework_architecture_unsupported": 6
}, },
"failureCount": 8, "failureCount": 7,
"failureRate": 0.5714, "failureRate": 0.5385,
"framework": "unknown", "framework": "unknown",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-18T11:36:11.987002+00:00", "lastTerminalAt": "2026-09-18T11:36:11.987002+00:00",
@@ -13360,10 +13402,10 @@
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 6, "successCount": 6,
"successRate": 0.4286, "successRate": 0.4615,
"targetGpu": "Iluvatar_mrv-100", "targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation", "taskType": "text-generation",
"total": 14, "total": 13,
"unresolvedFailureCount": 1 "unresolvedFailureCount": 1
}, },
"Kunlunxin_p-800|unknown|text-generation": { "Kunlunxin_p-800|unknown|text-generation": {
@@ -14710,6 +14752,31 @@
"total": 2, "total": 2,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Cambricon_mlu-370-x8|vllm|text-generation|qwen3|none": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"lastTerminalAt": "2026-09-20T22:24:01.251292+00:00",
"modelType": "qwen3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm|text-generation|spark2_5|fp8": { "Cambricon_mlu-370-x8|vllm|text-generation|spark2_5|fp8": {
"attributableFailureCount": 1, "attributableFailureCount": 1,
"consecutiveFailures": 1, "consecutiveFailures": 1,
@@ -20364,6 +20431,30 @@
"total": 2, "total": 2,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Cambricon_mlu-370-x8|vllm|text-generation|qwen3|none|29": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 29,
"modelType": "qwen3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm|text-generation|spark2_5|fp8|32": { "Cambricon_mlu-370-x8|vllm|text-generation|spark2_5|fp8|32": {
"attributableFailureCount": 1, "attributableFailureCount": 1,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
@@ -27574,20 +27665,20 @@
"unresolvedFailureCount": 1 "unresolvedFailureCount": 1
} }
}, },
"terminalRecords": 15977, "terminalRecords": 15978,
"totalRecords": 16133, "totalRecords": 16134,
"totals": { "totals": {
"attributableFailureCount": 5807, "attributableFailureCount": 5808,
"decisionFailureRate": 0.8617, "decisionFailureRate": 0.8617,
"decisionSuccessRate": 0.1383, "decisionSuccessRate": 0.1383,
"decisionTotal": 6739, "decisionTotal": 6740,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 3812, "ambiguous_runtime": 3812,
"architecture_compatibility": 212, "architecture_compatibility": 212,
"attention_backend": 1, "attention_backend": 1,
"backend_operator": 102, "backend_operator": 102,
"context_length": 318, "context_length": 318,
"framework_architecture_unsupported": 2019, "framework_architecture_unsupported": 2020,
"memory_capacity": 1196, "memory_capacity": 1196,
"model_load": 484, "model_load": 484,
"platform_infrastructure": 922, "platform_infrastructure": 922,
@@ -27598,14 +27689,14 @@
"日志缺失": 719, "日志缺失": 719,
"验证失败": 673 "验证失败": 673
}, },
"failureCount": 15045, "failureCount": 15046,
"failureRate": 0.9417, "failureRate": 0.9417,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 922, "platformFailureCount": 922,
"successCount": 932, "successCount": 932,
"successRate": 0.0583, "successRate": 0.0583,
"total": 15977, "total": 15978,
"unresolvedFailureCount": 8316 "unresolvedFailureCount": 8316
}, },
"warnings": [ "warnings": [
@@ -27653,12 +27744,12 @@
"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 Iluvatar_bi-150|transformers|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Iluvatar_bi-150|transformers|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 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": 16133, "summarizedRecords": 16134,
"version": 1 "version": 1
} }

65
.modelhub_state/queue_cleanup_latest.json
View File

@@ -14,13 +14,13 @@
100 100
], ],
"accounts": 12, "accounts": 12,
"activeScanned": 1145, "activeScanned": 1146,
"ageCleanupMode": "admission_only", "ageCleanupMode": "admission_only",
"agePolicySkipped": { "agePolicySkipped": {
"cleanupDisabled": true, "cleanupDisabled": true,
"reason": "admission_only" "reason": "admission_only"
}, },
"architectureBlockCount": 112, "architectureBlockCount": 113,
"architectureFrameworkCatalog": { "architectureFrameworkCatalog": {
"ascend_910-b3|text-generation": [ "ascend_910-b3|text-generation": [
"llamacpp", "llamacpp",
@@ -67,30 +67,8 @@
] ]
}, },
"architectureFrameworkCatalogErrors": {}, "architectureFrameworkCatalogErrors": {},
"architectureIncompatibleCount": 1, "architectureIncompatibleCount": 0,
"architectureIncompatibleTasks": [ "architectureIncompatibleTasks": [],
{
"accountIndex": 5,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-10-20T02:52:43.767336+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "model_type",
"architectureSignature": "model_type:gemma4_unified",
"architectureSignatures": [
"model_type:gemma4_unified"
],
"evaluatedFrameworks": [
"vllm_tokenizer_patch"
],
"framework": "vllm_tokenizer_patch",
"gpuType": "Ascend_910-b4",
"modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 4968995,
"taskType": "text-generation"
}
],
"architectureModelConfigErrors": { "architectureModelConfigErrors": {
"GestaltLabs/Ornstein-3.5-9B-V2-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/GestaltLabs/Ornstein-3.5-9B-V2-GGUF/resolve/master/config.json (status=404)", "GestaltLabs/Ornstein-3.5-9B-V2-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/GestaltLabs/Ornstein-3.5-9B-V2-GGUF/resolve/master/config.json (status=404)",
"LiquidAI/LFM2.5-2.6B-DSpark-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/LiquidAI/LFM2.5-2.6B-DSpark-GGUF/resolve/master/config.json (status=404)", "LiquidAI/LFM2.5-2.6B-DSpark-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/LiquidAI/LFM2.5-2.6B-DSpark-GGUF/resolve/master/config.json (status=404)",
@@ -119,42 +97,17 @@
"frameworkCatalogUnknown": 0, "frameworkCatalogUnknown": 0,
"frameworkContextUnknown": 72, "frameworkContextUnknown": 72,
"modelArchitectureUnknown": 134, "modelArchitectureUnknown": 134,
"noMatchingBlock": 985, "noMatchingBlock": 987,
"partiallyBlockedFrameworkSet": 25, "partiallyBlockedFrameworkSet": 25,
"runningMatchedProtected": 0, "runningMatchedProtected": 0,
"submissionContextMismatch": 0, "submissionContextMismatch": 0,
"submissionContextUnknown": 0 "submissionContextUnknown": 0
}, },
"cancelledCount": 1, "cancelledCount": 0,
"cancelledTasks": [ "cancelledTasks": [],
{
"accountIndex": 5,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-10-20T02:52:43.767336+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "model_type",
"architectureSignature": "model_type:gemma4_unified",
"architectureSignatures": [
"model_type:gemma4_unified"
],
"cleanupReasons": [
"known_framework_architecture_incompatible"
],
"evaluatedFrameworks": [
"vllm_tokenizer_patch"
],
"framework": "vllm_tokenizer_patch",
"gpuType": "Ascend_910-b4",
"modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 4968995,
"taskType": "text-generation"
}
],
"certainOomCount": 0, "certainOomCount": 0,
"certainOomTasks": [], "certainOomTasks": [],
"cleanupCandidateCount": 1, "cleanupCandidateCount": 0,
"dryRun": false, "dryRun": false,
"listingErrors": {}, "listingErrors": {},
"modelAgeErrors": {}, "modelAgeErrors": {},
@@ -179,7 +132,7 @@
], ],
"oldOverflowCount": 0, "oldOverflowCount": 0,
"oldOverflowTasks": [], "oldOverflowTasks": [],
"policyCancelledRecorded": 1, "policyCancelledRecorded": 0,
"policyNoLongerAppliesCount": 0, "policyNoLongerAppliesCount": 0,
"policyNoLongerAppliesTasks": [], "policyNoLongerAppliesTasks": [],
"recentModelDays": 7, "recentModelDays": 7,

2
.modelhub_state/recent_outcomes.jsonl
View File

@@ -77,6 +77,7 @@
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-20T19:47:52.978254+00:00", "modelId": "aisingapore/SEA-LION-v1-7B-IT-GPTQ", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "f7d2aee0bcf1396cd8ab3b1064b6a032eccc04f2d655a336023e13528574903d", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5469228368, "estimatedRequiredGiB": 6.118, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mpt", "modelscopeFileSize": 5473985594, "modelscopeLicense": "mit", "modelscopeParams": 1922048000, "modelscopeTags": ["license:mit", "model_type:mpt", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5473985594}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:09:56.541899+00:00", "targetGpu": "Biren_166m", "taskId": "4970509", "taskType": "text-generation", "verifyResult": -1} {"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-20T19:47:52.978254+00:00", "modelId": "aisingapore/SEA-LION-v1-7B-IT-GPTQ", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "f7d2aee0bcf1396cd8ab3b1064b6a032eccc04f2d655a336023e13528574903d", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5469228368, "estimatedRequiredGiB": 6.118, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mpt", "modelscopeFileSize": 5473985594, "modelscopeLicense": "mit", "modelscopeParams": 1922048000, "modelscopeTags": ["license:mit", "model_type:mpt", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5473985594}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:09:56.541899+00:00", "targetGpu": "Biren_166m", "taskId": "4970509", "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", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-20T12:34:29.856396+00:00", "modelId": "aisingapore/SEA-LION-v1-7B-IT-Research", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "17a693aa8ae65d96fb0c459d2e1f98ce1d8b2f8933e06b75903df1a5b48287eb", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15003361968, "estimatedRequiredGiB": 16.773, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mpt", "modelscopeFileSize": 15008118474, "modelscopeLicense": "cc-by-nc-sa-4.0", "modelscopeParams": 7501651968, "modelscopeTags": ["license:cc-by-nc-sa-4.0", "model_type:mpt", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15008118474}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:09:56.540284+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970507", "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", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-20T12:34:29.856396+00:00", "modelId": "aisingapore/SEA-LION-v1-7B-IT-Research", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "17a693aa8ae65d96fb0c459d2e1f98ce1d8b2f8933e06b75903df1a5b48287eb", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15003361968, "estimatedRequiredGiB": 16.773, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mpt", "modelscopeFileSize": 15008118474, "modelscopeLicense": "cc-by-nc-sa-4.0", "modelscopeParams": 7501651968, "modelscopeTags": ["license:cc-by-nc-sa-4.0", "model_type:mpt", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15008118474}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:09:56.540284+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970507", "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", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-20T12:34:29.856340+00:00", "modelId": "Arain119/Sophia", "modelProfile": {"architectures": ["SophiaForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2226652224, "estimatedRequiredGiB": 7.28, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "sophia_hybrid", "modelscopeFileSize": 6513869659, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 1113293776, "modelscopeTags": ["license:Apache License 2.0", "model_type:sophia_hybrid", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6513869659}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:09:56.493446+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970510", "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", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-20T12:34:29.856340+00:00", "modelId": "Arain119/Sophia", "modelProfile": {"architectures": ["SophiaForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2226652224, "estimatedRequiredGiB": 7.28, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "sophia_hybrid", "modelscopeFileSize": 6513869659, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 1113293776, "modelscopeTags": ["license:Apache License 2.0", "model_type:sophia_hybrid", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6513869659}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:09:56.493446+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970510", "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", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3"], "framework": "vllm", "lastSyncTime": "2026-09-20T22:24:01.251292+00:00", "modelId": "whcl412/mlx-LycheeAI-coder-1.7b", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 968080210, "estimatedRequiredGiB": 1.095, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 979581804, "modelscopeLicense": "apache-2.0", "modelscopeParams": 268944384, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:qwen3", "custom_tag:coder", "custom_tag:lora", "custom_tag:code", "custom_tag:lychee", "custom_tag:finetune", "custom_tag:multilingual"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 979581804}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:02:52.200512+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970447", "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", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["zaya"], "framework": "vllm", "lastSyncTime": "2026-09-20T17:09:45.266103+00:00", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "modelProfile": {"architectures": ["ZayaForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7915599888, "estimatedRequiredGiB": 8.885, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "zaya", "modelscopeFileSize": 7950463197, "modelscopeLicense": "other", "modelscopeParams": 2274126328, "modelscopeTags": ["license:other", "model_type:zaya", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:applescript", "custom_tag:macos", "custom_tag:computer-use", "custom_tag:agent", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:mlx", "custom_tag:moe", "custom_tag:osaurus"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7950463197}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:02:45.346171+00:00", "targetGpu": "Biren_166m", "taskId": "4970445", "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", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["zaya"], "framework": "vllm", "lastSyncTime": "2026-09-20T17:09:45.266103+00:00", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "modelProfile": {"architectures": ["ZayaForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7915599888, "estimatedRequiredGiB": 8.885, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "zaya", "modelscopeFileSize": 7950463197, "modelscopeLicense": "other", "modelscopeParams": 2274126328, "modelscopeTags": ["license:other", "model_type:zaya", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:applescript", "custom_tag:macos", "custom_tag:computer-use", "custom_tag:agent", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:mlx", "custom_tag:moe", "custom_tag:osaurus"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7950463197}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:02:45.346171+00:00", "targetGpu": "Biren_166m", "taskId": "4970445", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "memory_capacity", "failureAction": "reject_if_estimated_load_exceeds_memory", "failureCategory": "memory_capacity", "failureClassificationReason": "structured_oom", "failureCode": "PREFLIGHT_OOM", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureObservedGpuMemoryGiB": 32.0, "failureScope": "model_gpu", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-20T12:21:49.901701+00:00", "modelId": "inclusionAI/Ling-3.0-tiny", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15787992416, "estimatedRequiredGiB": 17.659, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bailing_hybrid", "modelscopeFileSize": 15801179822, "modelscopeLicense": "mit", "modelscopeParams": 7893392800, "modelscopeTags": ["license:mit", "model_type:bailing_hybrid", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15801179822}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:02:45.335178+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970437", "taskType": "text-generation", "verifyResult": -1} {"failReason": "memory_capacity", "failureAction": "reject_if_estimated_load_exceeds_memory", "failureCategory": "memory_capacity", "failureClassificationReason": "structured_oom", "failureCode": "PREFLIGHT_OOM", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureObservedGpuMemoryGiB": 32.0, "failureScope": "model_gpu", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-20T12:21:49.901701+00:00", "modelId": "inclusionAI/Ling-3.0-tiny", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15787992416, "estimatedRequiredGiB": 17.659, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bailing_hybrid", "modelscopeFileSize": 15801179822, "modelscopeLicense": "mit", "modelscopeParams": 7893392800, "modelscopeTags": ["license:mit", "model_type:bailing_hybrid", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15801179822}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:02:45.335178+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970437", "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", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:21:49.902137+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21561882284, "estimatedRequiredGiB": 24.122, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 21583784354, "modelscopeLicense": "other", "modelscopeParams": 17820210764, "modelscopeTags": ["license:other", "library:safetensors", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch", "custom_tag:nemotron-3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 21583784354}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:58:41.340891+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970366", "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", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:21:49.902137+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21561882284, "estimatedRequiredGiB": 24.122, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 21583784354, "modelscopeLicense": "other", "modelscopeParams": 17820210764, "modelscopeTags": ["license:other", "library:safetensors", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch", "custom_tag:nemotron-3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 21583784354}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:58:41.340891+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970366", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm", "lastSyncTime": "2026-09-15T11:19:29.645035+00:00", "modelId": "zstack/qwen3-4b-fake", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T11:11:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4590790", "taskType": "text-generation", "verifyResult": -1} {"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm", "lastSyncTime": "2026-09-15T11:19:29.645035+00:00", "modelId": "zstack/qwen3-4b-fake", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T11:11:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4590790", "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": "2026-09-15T10:50:55.652660+00:00", "modelId": "EschaLabs/Qwen3.8-27B-Escha-W2", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T10:49:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4609103", "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": "2026-09-15T10:50:55.652660+00:00", "modelId": "EschaLabs/Qwen3.8-27B-Escha-W2", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T10:49:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4609103", "taskType": "text-generation", "verifyResult": -1}
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-15T10:23:01.246264+00:00", "modelId": "FlagRelease/DeepSeek-R1-Distill-Qwen-1.5B-mthreads-FlagOS", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-15T10:15:23+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4590619", "taskType": "text-generation", "verifyResult": 1} {"failReason": null, "framework": "", "lastSyncTime": "2026-09-15T10:23:01.246264+00:00", "modelId": "FlagRelease/DeepSeek-R1-Distill-Qwen-1.5B-mthreads-FlagOS", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-15T10:15:23+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4590619", "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", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "", "lastSyncTime": "2026-09-15T09:34:12.938151+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T09:27:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4594446", "taskType": "text-generation", "verifyResult": -1}

1524
.modelhub_state/recovery_active_tasks.jsonl
View File

File diff suppressed because it is too large Load Diff

2024
.modelhub_state/recovery_intents.jsonl
View File

File diff suppressed because it is too large Load Diff

22
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": "d475799c099757428cf1f47b545c96c4be37dcd95d72659a669e4e496756ff05", ".modelhub_state/architecture_compatibility_blacklist.json": "3d437deb5f95356eb29f23ab9690362fc990496932ab5333bf65de171e02226b",
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
".modelhub_state/market_intelligence.json": "69827c7102edb23157dc95c6837012f714d0ee6ed497ef04237cc75d4ca4b1b0", ".modelhub_state/market_intelligence.json": "abb323deeed3b1accc29bfc9e9b5220d9e090ae39bcf6a8bb8a5d7385f47524b",
".modelhub_state/official_capabilities.json": "90aa9e4e77a863297b292dc928ed30e9fb6055fe6b7a4429e5ed6c976448eec5", ".modelhub_state/official_capabilities.json": "0f1af76dfb790395e123281161910dd4e67180b8e07a132c4ca092c84990efcc",
".modelhub_state/outcome_checkpoint.json": "98de58a3c6754a368ac9d71563bdf7c6e320d8328ee6d1c45f0de41f0fa895ee", ".modelhub_state/outcome_checkpoint.json": "b6c497379e059947cffa1ef8b2dedfe5799a6b555d4ff28e88986f39d6f28701",
".modelhub_state/queue_cleanup_latest.json": "acef5f83c30f7eb3ffae08f106b386239fe407d64362fb7038dd02f4f9164a98", ".modelhub_state/queue_cleanup_latest.json": "7ae814e016e640e3a3e232c56caa11f2f47ab12873461a8a8d8c4c1ecb4fc5e5",
".modelhub_state/recent_outcomes.jsonl": "e45967bf934b311b102b5a8649d2b1937ad378d12fdfa7becc2e0d789eee0b3d", ".modelhub_state/recent_outcomes.jsonl": "0eb051c31c47d94ebcd95eb0e3ebd2b8baf7f6c2c733add011b02311cc388af1",
".modelhub_state/recovery_active_tasks.jsonl": "353f59db2903d5e11dc9bbff0286f869c5b7126718dde34df0968d21b4c30260", ".modelhub_state/recovery_active_tasks.jsonl": "b2e71a5e7f2e2a0d375c62b9d6df9fc05b5bbc0335977ff15921801d283357c0",
".modelhub_state/recovery_intents.jsonl": "1b7a8b6464d2a5ef56acc996771997aa2d3ed3a2a0b30af69d78323179d3d996", ".modelhub_state/recovery_intents.jsonl": "ee5812b821b1b40085f9b86710211d8a737732bdb4e01b1c0396125041ae7faf",
".modelhub_state/routing_intelligence.json": "3ab2b753f8e643e6656448320426d621005ef66f10aed6ea7c494531e9a8abec", ".modelhub_state/routing_intelligence.json": "3ab2b753f8e643e6656448320426d621005ef66f10aed6ea7c494531e9a8abec",
".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989", ".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989",
".modelhub_state/worker_crashes.jsonl": "a494412048eca6dce83e7284303a6b4b56a445c1274ac201ab8723c739a14f23", ".modelhub_state/worker_crashes.jsonl": "a494412048eca6dce83e7284303a6b4b56a445c1274ac201ab8723c739a14f23",
"ledger/submissions.jsonl": "cf2d1119ef0e2f812a3b2f067334650d454631b59148f9e3e628a3cb5569be42", "ledger/submissions.jsonl": "cf2d1119ef0e2f812a3b2f067334650d454631b59148f9e3e628a3cb5569be42",
"outcomes/submissions.jsonl": "9d8515d4fc4f0e780f44beb38c2eda7de67cdf2743833e48449dd39fbee6c2ed" "outcomes/submissions.jsonl": "f0f94b54cff76ec1fc9665c8ad3f54cb62a840d1c9efaeb8a6c1de60eb18da75"
}, },
"generation": 10943, "generation": 10944,
"phase": "cycle", "phase": "cycle",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-09-20T22:23:00.581920+00:00", "updatedAt": "2026-09-20T22:24:13.580278+00:00",
"writerId": "fc715c06e24c4db2ae3e425e435db996" "writerId": "fc715c06e24c4db2ae3e425e435db996"
} }

5
outcomes/submissions.jsonl
View File

@@ -782,7 +782,6 @@
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:04:34.964210+00:00", "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7541230432, "estimatedRequiredGiB": 8.438, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 7550622334, "modelscopeLicense": "other", "modelscopeParams": 11520053248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 7550622334}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:02:45.337459+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970434", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:04:34.964210+00:00", "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7541230432, "estimatedRequiredGiB": 8.438, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 7550622334, "modelscopeLicense": "other", "modelscopeParams": 11520053248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 7550622334}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:02:45.337459+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970434", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:04:34.964227+00:00", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8447876488, "estimatedRequiredGiB": 9.452, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 8457284244, "modelscopeLicense": "other", "modelscopeParams": 13264949248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 8457284244}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:02:45.342540+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970435", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:04:34.964227+00:00", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8447876488, "estimatedRequiredGiB": 9.452, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 8457284244, "modelscopeLicense": "other", "modelscopeParams": 13264949248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 8457284244}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:02:45.342540+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970435", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:04:34.964283+00:00", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "modelProfile": {"architectures": ["MuseGlimmerForConditionalGeneration"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21407235494, "estimatedRequiredGiB": 23.956, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "muse_glimmer", "modelscopeFileSize": 21435726263, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5792290816, "modelscopeTags": ["license:apache-2.0", "model_type:muse_glimmer", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:muse_glimmer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21435726263}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:02:52.182815+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970446", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:04:34.964283+00:00", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "modelProfile": {"architectures": ["MuseGlimmerForConditionalGeneration"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21407235494, "estimatedRequiredGiB": 23.956, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "muse_glimmer", "modelscopeFileSize": 21435726263, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5792290816, "modelscopeTags": ["license:apache-2.0", "model_type:muse_glimmer", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:muse_glimmer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21435726263}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:02:52.182815+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970446", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:04:34.964183+00:00", "modelId": "whcl412/mlx-LycheeAI-coder-1.7b", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 968080210, "estimatedRequiredGiB": 1.095, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 979581804, "modelscopeLicense": "apache-2.0", "modelscopeParams": 268944384, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:qwen3", "custom_tag:coder", "custom_tag:lora", "custom_tag:code", "custom_tag:lychee", "custom_tag:finetune", "custom_tag:multilingual"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 979581804}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:02:52.200512+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970447", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:21:49.901779+00:00", "modelId": "RedHatAI/starcoder2-3b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3484485728, "estimatedRequiredGiB": 3.898, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 3487786133, "modelscopeLicense": "other", "modelscopeParams": 3181366272, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3487786133}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:09:56.479634+00:00", "targetGpu": "Vastai_va16", "taskId": "4970501", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:21:49.901779+00:00", "modelId": "RedHatAI/starcoder2-3b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3484485728, "estimatedRequiredGiB": 3.898, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 3487786133, "modelscopeLicense": "other", "modelscopeParams": 3181366272, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3487786133}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:09:56.479634+00:00", "targetGpu": "Vastai_va16", "taskId": "4970501", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:21:49.901761+00:00", "modelId": "mlx-community/gemma-4-e4b-it-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7486327132, "estimatedRequiredGiB": 8.403, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 7518908360, "modelscopeLicense": "gemma", "modelscopeParams": 2227418442, "modelscopeTags": ["license:gemma", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7518908360}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:09:56.489765+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970500", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:21:49.901761+00:00", "modelId": "mlx-community/gemma-4-e4b-it-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7486327132, "estimatedRequiredGiB": 8.403, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 7518908360, "modelscopeLicense": "gemma", "modelscopeParams": 2227418442, "modelscopeTags": ["license:gemma", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7518908360}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:09:56.489765+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970500", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:21:49.901839+00:00", "modelId": "mlx-community/gemma-4-12B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9003966484, "estimatedRequiredGiB": 10.099, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 9036402901, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2463563824, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9036402901}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:09:56.544236+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970508", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:21:49.901839+00:00", "modelId": "mlx-community/gemma-4-12B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9003966484, "estimatedRequiredGiB": 10.099, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 9036402901, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2463563824, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9036402901}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:09:56.544236+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970508", "taskType": "text-generation", "verifyResult": null}
@@ -937,8 +936,8 @@
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T21:33:11.158043+00:00", "modelId": "aisingapore/SEA-LION-v1-7B-IT-GPTQ", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5469228368, "estimatedRequiredGiB": 6.118, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mpt", "modelscopeFileSize": 5473985594, "modelscopeLicense": "mit", "modelscopeParams": 1922048000, "modelscopeTags": ["license:mit", "model_type:mpt", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5473985594}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T13:23:33.095200+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4979625", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T21:33:11.158043+00:00", "modelId": "aisingapore/SEA-LION-v1-7B-IT-GPTQ", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5469228368, "estimatedRequiredGiB": 6.118, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mpt", "modelscopeFileSize": 5473985594, "modelscopeLicense": "mit", "modelscopeParams": 1922048000, "modelscopeTags": ["license:mit", "model_type:mpt", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5473985594}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T13:23:33.095200+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4979625", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T21:55:28.960225+00:00", "modelId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9081287016, "estimatedRequiredGiB": 10.159, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9090504988, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9090504988}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T13:36:07.724905+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4979835", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T21:55:28.960225+00:00", "modelId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9081287016, "estimatedRequiredGiB": 10.159, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9090504988, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9090504988}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T13:36:07.724905+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4979835", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T22:16:58.665912+00:00", "modelId": "neuralmagic/starcoder2-3b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4093158536, "estimatedRequiredGiB": 4.578, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 4096457730, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 3181366272, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4096457730}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T14:01:30.719848+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4980119", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T22:16:58.665912+00:00", "modelId": "neuralmagic/starcoder2-3b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4093158536, "estimatedRequiredGiB": 4.578, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 4096457730, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 3181366272, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4096457730}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T14:01:30.719848+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4980119", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "neuralmagic/gemma-2-2b-it-quantized.w4a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3403624536, "estimatedRequiredGiB": 3.828, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 3425449487, "modelscopeLicense": "llama2", "modelscopeParams": 3204165888, "modelscopeTags": ["license:llama2", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3425449487}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T14:22:01.079527+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4980340", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T22:24:01.251307+00:00", "modelId": "neuralmagic/gemma-2-2b-it-quantized.w4a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3403624536, "estimatedRequiredGiB": 3.828, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 3425449487, "modelscopeLicense": "llama2", "modelscopeParams": 3204165888, "modelscopeTags": ["license:llama2", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3425449487}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T14:22:01.079527+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4980340", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "nm-testing/tinyllama-oneshot-w8a16-per-channel", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1232060880, "estimatedRequiredGiB": 1.379, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1233909203, "modelscopeLicense": null, "modelscopeParams": 1100048384, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 1233909203}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T14:22:13.035851+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4980360", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T22:24:01.251269+00:00", "modelId": "nm-testing/tinyllama-oneshot-w8a16-per-channel", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1232060880, "estimatedRequiredGiB": 1.379, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1233909203, "modelscopeLicense": null, "modelscopeParams": 1100048384, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 1233909203}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T14:22:13.035851+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4980360", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20886763512, "estimatedRequiredGiB": 23.388, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 20926892207, "modelscopeLicense": "gemma", "modelscopeParams": 28842037282, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20926892207}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T14:24:07.110246+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4980393", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20886763512, "estimatedRequiredGiB": 23.388, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 20926892207, "modelscopeLicense": "gemma", "modelscopeParams": 28842037282, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20926892207}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T14:24:07.110246+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4980393", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26057989872, "estimatedRequiredGiB": 29.158, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "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": "pending", "submitTime": "2026-09-20T14:25:29.832253+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4980394", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26057989872, "estimatedRequiredGiB": 29.158, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "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": "pending", "submitTime": "2026-09-20T14:25:29.832253+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4980394", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "logic65/Qwen3.8-Whittle-w50-18.3B-unrepaired", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 36679335352, "estimatedRequiredGiB": 41.028, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 36711610638, "modelscopeLicense": "apache-2.0", "modelscopeParams": 18339618304, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:pruning", "custom_tag:width-pruning", "custom_tag:zero-training", "custom_tag:qwen3_5", "custom_tag:gated-deltanet"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 36711610638}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T14:25:29.955385+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4980395", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "logic65/Qwen3.8-Whittle-w50-18.3B-unrepaired", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 36679335352, "estimatedRequiredGiB": 41.028, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 36711610638, "modelscopeLicense": "apache-2.0", "modelscopeParams": 18339618304, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:pruning", "custom_tag:width-pruning", "custom_tag:zero-training", "custom_tag:qwen3_5", "custom_tag:gated-deltanet"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 36711610638}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T14:25:29.955385+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4980395", "taskType": "text-generation", "verifyResult": null}