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

state: generation 8270 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-16 16:01:14 +00:00
parent 04a5db0f14
commit c8798b7683
9 changed files with 2086 additions and 2042 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -1695,7 +1695,7 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-09-16T15:58:24.307094+00:00", "generatedAt": "2026-09-16T16:01:13.693223+00:00",
"summary": { "summary": {
"activeBlockCount": 82, "activeBlockCount": 82,
"byGpuFramework": { "byGpuFramework": {

6
.modelhub_state/architecture_history_backfill.json
View File

@@ -75,7 +75,7 @@
"7": { "7": {
"complete": false, "complete": false,
"lastError": "ModelHubAPIError: 系统错误", "lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 603, "listingErrors": 604,
"nextPage": 1, "nextPage": 1,
"recordsScanned": 0, "recordsScanned": 0,
"uniqueRecords": 0 "uniqueRecords": 0
@@ -102,12 +102,12 @@
"cutoffAt": "2026-09-04T03:55:51.365685+00:00", "cutoffAt": "2026-09-04T03:55:51.365685+00:00",
"failureLogsInspected": 0, "failureLogsInspected": 0,
"mode": "incremental_decision_only", "mode": "incremental_decision_only",
"nextAccountIndex": 7, "nextAccountIndex": 8,
"recordsScanned": 0, "recordsScanned": 0,
"seenTaskIds": [], "seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00", "startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0, "terminalRecords": 0,
"uniqueRecords": 0, "uniqueRecords": 0,
"updatedAt": "2026-09-16T15:58:24.275441+00:00", "updatedAt": "2026-09-16T16:01:13.660774+00:00",
"version": 1 "version": 1
} }

2
.modelhub_state/market_intelligence.json
View File

@@ -416,7 +416,7 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-09-16T15:56:36.552513+00:00", "generatedAt": "2026-09-16T15:59:36.008111+00:00",
"gpuStats": { "gpuStats": {
"Ascend_910-b3": { "Ascend_910-b3": {
"available": true, "available": true,

1506
.modelhub_state/official_capabilities.json
View File

File diff suppressed because it is too large Load Diff

215
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{ {
"generatedAt": "2026-09-16T14:22:24.640225+00:00", "generatedAt": "2026-09-16T15:59:27.850405+00:00",
"lastSyncTime": "2026-09-16T14:22:22.658468+00:00", "lastSyncTime": "2026-09-16T15:59:25.244426+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -1928,25 +1928,25 @@
"unresolvedFailureCount": 59 "unresolvedFailureCount": 59
}, },
"Biren_166m|vllm|text-generation": { "Biren_166m|vllm|text-generation": {
"attributableFailureCount": 11, "attributableFailureCount": 13,
"decisionFailureRate": 0.9167, "decisionFailureRate": 0.9286,
"decisionSuccessRate": 0.0833, "decisionSuccessRate": 0.0714,
"decisionTotal": 12, "decisionTotal": 14,
"failureBreakdown": { "failureBreakdown": {
"framework_architecture_unsupported": 7, "framework_architecture_unsupported": 8,
"model_load": 4 "model_load": 5
}, },
"failureCount": 11, "failureCount": 13,
"failureRate": 0.9167, "failureRate": 0.9286,
"framework": "vllm", "framework": "vllm",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 1, "successCount": 1,
"successRate": 0.0833, "successRate": 0.0714,
"targetGpu": "Biren_166m", "targetGpu": "Biren_166m",
"taskType": "text-generation", "taskType": "text-generation",
"total": 12, "total": 14,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Cambricon_mlu-370-x4|unknown|text-generation": { "Cambricon_mlu-370-x4|unknown|text-generation": {
@@ -2181,25 +2181,25 @@
"decisionSuccessRate": 0.1154, "decisionSuccessRate": 0.1154,
"decisionTotal": 26, "decisionTotal": 26,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 10, "ambiguous_runtime": 11,
"backend_operator": 4, "backend_operator": 4,
"framework_architecture_unsupported": 6, "framework_architecture_unsupported": 6,
"model_load": 4, "model_load": 4,
"runtime_memory": 9, "runtime_memory": 9,
"参数/模板问题": 1 "参数/模板问题": 1
}, },
"failureCount": 34, "failureCount": 35,
"failureRate": 0.9189, "failureRate": 0.9211,
"framework": "vllm_0_17_0_corex_4_4_0", "framework": "vllm_0_17_0_corex_4_4_0",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 3, "successCount": 3,
"successRate": 0.0811, "successRate": 0.0789,
"targetGpu": "Iluvatar_bi-150", "targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation", "taskType": "text-generation",
"total": 37, "total": 38,
"unresolvedFailureCount": 11 "unresolvedFailureCount": 12
}, },
"Iluvatar_bi-150|vllm|text-generation": { "Iluvatar_bi-150|vllm|text-generation": {
"attributableFailureCount": 26, "attributableFailureCount": 26,
@@ -2786,30 +2786,30 @@
"unresolvedFailureCount": 896 "unresolvedFailureCount": 896
}, },
"vllm": { "vllm": {
"attributableFailureCount": 364, "attributableFailureCount": 366,
"decisionFailureRate": 0.9604, "decisionFailureRate": 0.9606,
"decisionSuccessRate": 0.0396, "decisionSuccessRate": 0.0394,
"decisionTotal": 379, "decisionTotal": 381,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 222, "ambiguous_runtime": 222,
"backend_operator": 35, "backend_operator": 35,
"framework_architecture_unsupported": 269, "framework_architecture_unsupported": 270,
"memory_capacity": 7, "memory_capacity": 7,
"model_load": 30, "model_load": 31,
"platform_infrastructure": 2, "platform_infrastructure": 2,
"repository_structure": 8, "repository_structure": 8,
"runtime_memory": 6, "runtime_memory": 6,
"tokenizer_compatibility": 9, "tokenizer_compatibility": 9,
"参数/模板问题": 31 "参数/模板问题": 31
}, },
"failureCount": 619, "failureCount": 621,
"failureRate": 0.9763, "failureRate": 0.9764,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 2, "platformFailureCount": 2,
"successCount": 15, "successCount": 15,
"successRate": 0.0237, "successRate": 0.0236,
"total": 634, "total": 636,
"unresolvedFailureCount": 253 "unresolvedFailureCount": 253
}, },
"vllm-mlu": { "vllm-mlu": {
@@ -2859,22 +2859,22 @@
"decisionSuccessRate": 0.1154, "decisionSuccessRate": 0.1154,
"decisionTotal": 26, "decisionTotal": 26,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 10, "ambiguous_runtime": 11,
"backend_operator": 4, "backend_operator": 4,
"framework_architecture_unsupported": 6, "framework_architecture_unsupported": 6,
"model_load": 4, "model_load": 4,
"runtime_memory": 9, "runtime_memory": 9,
"参数/模板问题": 1 "参数/模板问题": 1
}, },
"failureCount": 34, "failureCount": 35,
"failureRate": 0.9189, "failureRate": 0.9211,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 3, "successCount": 3,
"successRate": 0.0811, "successRate": 0.0789,
"total": 37, "total": 38,
"unresolvedFailureCount": 11 "unresolvedFailureCount": 12
}, },
"vllm_fix_tokenizer": { "vllm_fix_tokenizer": {
"attributableFailureCount": 57, "attributableFailureCount": 57,
@@ -2920,7 +2920,7 @@
"unresolvedFailureCount": 5 "unresolvedFailureCount": 5
} }
}, },
"generatedAt": "2026-09-16T14:22:24.635026+00:00", "generatedAt": "2026-09-16T15:59:27.843862+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 49, "attributableFailureCount": 49,
@@ -2971,28 +2971,28 @@
"unresolvedFailureCount": 230 "unresolvedFailureCount": 230
}, },
"Biren_166m": { "Biren_166m": {
"attributableFailureCount": 47, "attributableFailureCount": 49,
"decisionFailureRate": 0.94, "decisionFailureRate": 0.9423,
"decisionSuccessRate": 0.06, "decisionSuccessRate": 0.0577,
"decisionTotal": 50, "decisionTotal": 52,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 31, "ambiguous_runtime": 31,
"backend_operator": 4, "backend_operator": 4,
"framework_architecture_unsupported": 34, "framework_architecture_unsupported": 35,
"memory_capacity": 1, "memory_capacity": 1,
"model_load": 7, "model_load": 8,
"tokenizer_compatibility": 1, "tokenizer_compatibility": 1,
"参数/模板问题": 1, "参数/模板问题": 1,
"验证失败": 27 "验证失败": 27
}, },
"failureCount": 106, "failureCount": 108,
"failureRate": 0.9725, "failureRate": 0.973,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 3, "successCount": 3,
"successRate": 0.0275, "successRate": 0.027,
"total": 109, "total": 111,
"unresolvedFailureCount": 59 "unresolvedFailureCount": 59
}, },
"Cambricon_mlu-370-x4": { "Cambricon_mlu-370-x4": {
@@ -3066,7 +3066,7 @@
"decisionSuccessRate": 0.1525, "decisionSuccessRate": 0.1525,
"decisionTotal": 59, "decisionTotal": 59,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 18, "ambiguous_runtime": 19,
"backend_operator": 7, "backend_operator": 7,
"framework_architecture_unsupported": 20, "framework_architecture_unsupported": 20,
"model_load": 11, "model_load": 11,
@@ -3075,15 +3075,15 @@
"参数/模板问题": 3, "参数/模板问题": 3,
"验证失败": 30 "验证失败": 30
}, },
"failureCount": 101, "failureCount": 102,
"failureRate": 0.9182, "failureRate": 0.9189,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 9, "successCount": 9,
"successRate": 0.0818, "successRate": 0.0811,
"total": 110, "total": 111,
"unresolvedFailureCount": 51 "unresolvedFailureCount": 52
}, },
"Iluvatar_mrv-100": { "Iluvatar_mrv-100": {
"attributableFailureCount": 111, "attributableFailureCount": 111,
@@ -3436,14 +3436,14 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Biren_166m|vllm|text-generation|llama|awq": { "Biren_166m|vllm|text-generation|llama|awq": {
"attributableFailureCount": 3, "attributableFailureCount": 4,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 3, "decisionTotal": 4,
"failureBreakdown": { "failureBreakdown": {
"model_load": 3 "model_load": 4
}, },
"failureCount": 3, "failureCount": 4,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"modelType": "llama", "modelType": "llama",
@@ -3455,7 +3455,7 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Biren_166m", "targetGpu": "Biren_166m",
"taskType": "text-generation", "taskType": "text-generation",
"total": 3, "total": 4,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Biren_166m|vllm|text-generation|nanbeige|compressed-tensors": { "Biren_166m|vllm|text-generation|nanbeige|compressed-tensors": {
@@ -3571,6 +3571,29 @@
"total": 1, "total": 1,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Biren_166m|vllm|text-generation|qwen3_5|exl3": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "exl3",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5|gptq": { "Biren_166m|vllm|text-generation|qwen3_5|gptq": {
"attributableFailureCount": 1, "attributableFailureCount": 1,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
@@ -4263,9 +4286,9 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 0, "decisionTotal": 0,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 1 "ambiguous_runtime": 2
}, },
"failureCount": 1, "failureCount": 2,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0", "framework": "vllm_0_17_0_corex_4_4_0",
"modelType": "qwen3_5_moe", "modelType": "qwen3_5_moe",
@@ -4277,8 +4300,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Iluvatar_bi-150", "targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation", "taskType": "text-generation",
"total": 1, "total": 2,
"unresolvedFailureCount": 1 "unresolvedFailureCount": 2
}, },
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5_moe|none": { "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5_moe|none": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -7002,14 +7025,14 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Biren_166m|vllm|text-generation|llama|awq|32": { "Biren_166m|vllm|text-generation|llama|awq|32": {
"attributableFailureCount": 3, "attributableFailureCount": 4,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 3, "decisionTotal": 4,
"failureBreakdown": { "failureBreakdown": {
"model_load": 3 "model_load": 4
}, },
"failureCount": 3, "failureCount": 4,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"loadSizeLog2Bucket": 32, "loadSizeLog2Bucket": 32,
@@ -7022,7 +7045,7 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Biren_166m", "targetGpu": "Biren_166m",
"taskType": "text-generation", "taskType": "text-generation",
"total": 3, "total": 4,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Biren_166m|vllm|text-generation|nanbeige|compressed-tensors|32": { "Biren_166m|vllm|text-generation|nanbeige|compressed-tensors|32": {
@@ -7167,6 +7190,30 @@
"total": 1, "total": 1,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Biren_166m|vllm|text-generation|qwen3_5|exl3|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 33,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "exl3",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5|gptq|34": { "Biren_166m|vllm|text-generation|qwen3_5|gptq|34": {
"attributableFailureCount": 1, "attributableFailureCount": 1,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
@@ -8127,9 +8174,9 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 0, "decisionTotal": 0,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 1 "ambiguous_runtime": 2
}, },
"failureCount": 1, "failureCount": 2,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0", "framework": "vllm_0_17_0_corex_4_4_0",
"loadSizeLog2Bucket": 34, "loadSizeLog2Bucket": 34,
@@ -8142,8 +8189,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Iluvatar_bi-150", "targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation", "taskType": "text-generation",
"total": 1, "total": 2,
"unresolvedFailureCount": 1 "unresolvedFailureCount": 2
}, },
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5_moe|none|34": { "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5_moe|none|34": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -10898,19 +10945,19 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 2020, "terminalRecords": 2023,
"totalRecords": 2114, "totalRecords": 2117,
"totals": { "totals": {
"attributableFailureCount": 650, "attributableFailureCount": 652,
"decisionFailureRate": 0.8916, "decisionFailureRate": 0.8919,
"decisionSuccessRate": 0.1084, "decisionSuccessRate": 0.1081,
"decisionTotal": 729, "decisionTotal": 731,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 491, "ambiguous_runtime": 492,
"backend_operator": 45, "backend_operator": 45,
"framework_architecture_unsupported": 426, "framework_architecture_unsupported": 427,
"memory_capacity": 12, "memory_capacity": 12,
"model_load": 84, "model_load": 85,
"platform_infrastructure": 10, "platform_infrastructure": 10,
"repository_structure": 8, "repository_structure": 8,
"runtime_memory": 15, "runtime_memory": 15,
@@ -10918,28 +10965,28 @@
"参数/模板问题": 117, "参数/模板问题": 117,
"验证失败": 673 "验证失败": 673
}, },
"failureCount": 1941, "failureCount": 1944,
"failureRate": 0.9609, "failureRate": 0.9609,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 10, "platformFailureCount": 10,
"successCount": 79, "successCount": 79,
"successRate": 0.0391, "successRate": 0.0391,
"total": 2020, "total": 2023,
"unresolvedFailureCount": 1281 "unresolvedFailureCount": 1282
}, },
"warnings": [ "warnings": [
"GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。", "GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。", "GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
"组合 Biren_166m|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 Biren_166m|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 Biren_166m|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 Biren_166m|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -10965,6 +11012,6 @@
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 2114, "summarizedRecords": 2117,
"version": 1 "version": 1
} }

1132
.modelhub_state/recovery_active_tasks.jsonl
View File

File diff suppressed because it is too large Load Diff

1242
.modelhub_state/recovery_intents.jsonl
View File

File diff suppressed because it is too large Load Diff

20
manifest.json
View File

@@ -1,24 +1,24 @@
{ {
"agentVersion": "2026.09.04.4", "agentVersion": "2026.09.04.4",
"checksums": { "checksums": {
".modelhub_state/architecture_compatibility_blacklist.json": "76a38ae8a2bfd7a299542b371c57e146b9c9d735d1c541165ebe8ed43018e30f", ".modelhub_state/architecture_compatibility_blacklist.json": "c2f700e1e51144bad47637253499f0db80412ef697964c51edb58feb33334fd8",
".modelhub_state/architecture_history_backfill.json": "6a40a4908d7ea61839679d0f284cdf6f90971468cc5f6944cba8c538c9475373", ".modelhub_state/architecture_history_backfill.json": "dffa85a534803d7bf3e3938ca7946f4cecddaf723b0c01f36762be1e587d755b",
".modelhub_state/market_intelligence.json": "1d0c913566099427d73891702d76802b72fb9e35e5fa09d37ab0947fabba5846", ".modelhub_state/market_intelligence.json": "01633141a81bba91e41523faf8c1cc3495b25a1c1832aa0dc0a380b9b3714d57",
".modelhub_state/official_capabilities.json": "339bbf34200da74c126ebc1cc2e9d4f6cebb073924c482617325681b63caeeff", ".modelhub_state/official_capabilities.json": "56b899361296bc74db6cefc87bfd4f8896c641535c7ca3c574f6d67da4fac27f",
".modelhub_state/outcome_checkpoint.json": "261463be3e7ed9eb433b0aa11028c741904852b629051cfef4cfd6a473f5f542", ".modelhub_state/outcome_checkpoint.json": "f10a974be026c8948f0b705e29d4d14a4f06b167980009c797b6f25b0521c080",
".modelhub_state/queue_cleanup_latest.json": "057079282bc277b3a97c1805915c45464c12312f8ee3ba54d0366d05f34f4466", ".modelhub_state/queue_cleanup_latest.json": "057079282bc277b3a97c1805915c45464c12312f8ee3ba54d0366d05f34f4466",
".modelhub_state/recent_outcomes.jsonl": "f13c8a5624d8090382f698e92471a1e8e88db1c57f5e9f580d3403eee853f0d3", ".modelhub_state/recent_outcomes.jsonl": "f13c8a5624d8090382f698e92471a1e8e88db1c57f5e9f580d3403eee853f0d3",
".modelhub_state/recovery_active_tasks.jsonl": "1444c8fe87fb548b7e2e74c988fd4c942fb23593e3dfb1dacec483c6b3905ed7", ".modelhub_state/recovery_active_tasks.jsonl": "86ae04f1f18afb0b9ff2343e6a740f94d9c81a121eaac72ebb6eb4e246e5ee3a",
".modelhub_state/recovery_intents.jsonl": "2a0083ed43238bb13572048dbfeb1d797ed4378aba415ac2e9e996757eeaaa12", ".modelhub_state/recovery_intents.jsonl": "b6f037c281321ace57067edc64c281049d84513b1b75bed3d1879fd81b1a2477",
".modelhub_state/routing_intelligence.json": "0f9c1a6db5a3f0702858929f0f6e71cb30d8bba861a40d0e2d18dd7d547ec4b4", ".modelhub_state/routing_intelligence.json": "0f9c1a6db5a3f0702858929f0f6e71cb30d8bba861a40d0e2d18dd7d547ec4b4",
".modelhub_state/submission_exclusions.jsonl": "632739c6cd6a2dd2237572ba18e6a390c5aa37ce56a18a2c1341d78569421552", ".modelhub_state/submission_exclusions.jsonl": "632739c6cd6a2dd2237572ba18e6a390c5aa37ce56a18a2c1341d78569421552",
".modelhub_state/worker_crashes.jsonl": "b41d1dda7bab11bedd96de40fecd2d416e47396901b3283f48a56de5d6348983", ".modelhub_state/worker_crashes.jsonl": "b41d1dda7bab11bedd96de40fecd2d416e47396901b3283f48a56de5d6348983",
"ledger/submissions.jsonl": "371dd143df99de47a64390c7a7ff8c6998f2fc2e9b68a33856c145691b1527a5", "ledger/submissions.jsonl": "371dd143df99de47a64390c7a7ff8c6998f2fc2e9b68a33856c145691b1527a5",
"outcomes/submissions.jsonl": "fe1ebc8e20834bd71d9dcac6e5fccbffa84f5a30d61a4938c0ffd56a1d5e0881" "outcomes/submissions.jsonl": "c384d9aa6e4a9ee92e5b0c4f71592f67f1fa518ecb5f557f7dc4a4723bae1ff6"
}, },
"generation": 8269, "generation": 8270,
"phase": "cycle", "phase": "cycle",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-09-16T15:58:24.417267+00:00", "updatedAt": "2026-09-16T16:01:14.664425+00:00",
"writerId": "eccb3e0018f640d19e578c271a207b5c" "writerId": "eccb3e0018f640d19e578c271a207b5c"
} }

3
outcomes/submissions.jsonl
View File

@@ -1,5 +1,4 @@
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-04T11:58:24.844524+00:00", "modelId": "inclusionAI/Ling-3.0-tiny-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "efcec92f0f61cfcfef2bff75fcc3b460aac2425880772995e6373e3f88061c16", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8408187808, "estimatedRequiredGiB": 46.011, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "manufacturer_spec", "sourceUrl": "https://docs.mthreads.com/s4000/s4000-doc-online/product_specifications/"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 41170267110, "modelscopeLicense": "mit", "modelscopeParams": null, "modelscopeTags": ["license:mit", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 41170267110}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T03:57:15.312611+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4610785", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-04T11:58:24.844524+00:00", "modelId": "inclusionAI/Ling-3.0-tiny-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "efcec92f0f61cfcfef2bff75fcc3b460aac2425880772995e6373e3f88061c16", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8408187808, "estimatedRequiredGiB": 46.011, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "manufacturer_spec", "sourceUrl": "https://docs.mthreads.com/s4000/s4000-doc-online/product_specifications/"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 41170267110, "modelscopeLicense": "mit", "modelscopeParams": null, "modelscopeTags": ["license:mit", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 41170267110}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T03:57:15.312611+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4610785", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T11:58:24.844440+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "manufacturer_spec", "sourceUrl": "https://www.birentech.com/news/id6rz98v3obczy77cmxzfgk3/"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737317601, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "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:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737317601}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T03:57:15.115591+00:00", "targetGpu": "Biren_166m", "taskId": "4610789", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-04T12:29:56.904005+00:00", "modelId": "bharatgenai/Param2-17B-A2.4B-Thinking", "modelProfile": {"architectures": ["Param2MoEForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 34302758832, "estimatedRequiredGiB": 38.353, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "param2moe", "modelscopeFileSize": 34317809830, "modelscopeLicense": null, "modelscopeParams": 17151125376, "modelscopeTags": ["model_type:param2moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:mixture-of-experts", "custom_tag:multilingual", "custom_tag:indian-languages"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 34317809830}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T04:29:16.672536+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4611191", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-04T12:29:56.904005+00:00", "modelId": "bharatgenai/Param2-17B-A2.4B-Thinking", "modelProfile": {"architectures": ["Param2MoEForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 34302758832, "estimatedRequiredGiB": 38.353, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "param2moe", "modelscopeFileSize": 34317809830, "modelscopeLicense": null, "modelscopeParams": 17151125376, "modelscopeTags": ["model_type:param2moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:mixture-of-experts", "custom_tag:multilingual", "custom_tag:indian-languages"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 34317809830}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T04:29:16.672536+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4611191", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-04T12:29:56.903997+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727938576, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737300809, "modelscopeLicense": "other", "modelscopeParams": 8030261248, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "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:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737300809}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T04:29:16.656478+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4611189", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-04T12:29:56.903997+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727938576, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737300809, "modelscopeLicense": "other", "modelscopeParams": 8030261248, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "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:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737300809}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T04:29:16.656478+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4611189", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-04T12:43:05.302336+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737317601, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "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:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737317601}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T04:34:21.517356+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4611266", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-04T12:43:05.302336+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737317601, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "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:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737317601}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T04:34:21.517356+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4611266", "taskType": "text-generation", "verifyResult": null}
@@ -11,7 +10,6 @@
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T14:58:13.792154+00:00", "modelId": "VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 31228126952, "estimatedRequiredGiB": 34.934, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "manufacturer_spec", "sourceUrl": "https://www.birentech.com/news/id6rz98v3obczy77cmxzfgk3/"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 31258377392, "modelscopeLicense": "apache-2.0", "modelscopeParams": 27781427952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:w8a8", "custom_tag:int8", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 31258377392}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T06:55:47.759663+00:00", "targetGpu": "Biren_166m", "taskId": "4621595", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T14:58:13.792154+00:00", "modelId": "VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 31228126952, "estimatedRequiredGiB": 34.934, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "manufacturer_spec", "sourceUrl": "https://www.birentech.com/news/id6rz98v3obczy77cmxzfgk3/"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 31258377392, "modelscopeLicense": "apache-2.0", "modelscopeParams": 27781427952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:w8a8", "custom_tag:int8", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 31258377392}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T06:55:47.759663+00:00", "targetGpu": "Biren_166m", "taskId": "4621595", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T15:14:29.722109+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality-FP16", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29952487299, "estimatedRequiredGiB": 33.498, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "manufacturer_spec", "sourceUrl": "https://www.birentech.com/news/id6rz98v3obczy77cmxzfgk3/"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 29973198172, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8027131120, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:m1", "custom_tag:m2", "custom_tag:fp16", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:coding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 29973198172}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T07:12:30.054811+00:00", "targetGpu": "Biren_166m", "taskId": "4621809", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T15:14:29.722109+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality-FP16", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29952487299, "estimatedRequiredGiB": 33.498, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "manufacturer_spec", "sourceUrl": "https://www.birentech.com/news/id6rz98v3obczy77cmxzfgk3/"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 29973198172, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8027131120, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:m1", "custom_tag:m2", "custom_tag:fp16", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:coding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 29973198172}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T07:12:30.054811+00:00", "targetGpu": "Biren_166m", "taskId": "4621809", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-04T16:14:29.511220+00:00", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15338408461, "estimatedRequiredGiB": 17.168, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "modelhub_preflight_oom:49"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 15362064483, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7669052656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:exl3", "custom_tag:exllamav3", "custom_tag:quantization", "custom_tag:long-context", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "exl3", "repositoryOnDiskBytes": 15362064483}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T08:14:12.544960+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4622655", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-04T16:14:29.511220+00:00", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15338408461, "estimatedRequiredGiB": 17.168, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "modelhub_preflight_oom:49"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 15362064483, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7669052656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:exl3", "custom_tag:exllamav3", "custom_tag:quantization", "custom_tag:long-context", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "exl3", "repositoryOnDiskBytes": 15362064483}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T08:14:12.544960+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4622655", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T16:33:41.731498+00:00", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15338408461, "estimatedRequiredGiB": 17.168, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "manufacturer_spec", "sourceUrl": "https://www.birentech.com/news/id6rz98v3obczy77cmxzfgk3/"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 15362064483, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7669052656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:exl3", "custom_tag:exllamav3", "custom_tag:quantization", "custom_tag:long-context", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "exl3", "repositoryOnDiskBytes": 15362064483}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T08:33:06.846794+00:00", "targetGpu": "Biren_166m", "taskId": "4623002", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-04T20:39:27.718139+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8818103892, "estimatedRequiredGiB": 9.883, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:8"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 8842796317, "modelscopeLicense": "mit", "modelscopeParams": 6728625904, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 8842796317}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T12:34:49.403585+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4626360", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-04T20:39:27.718139+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8818103892, "estimatedRequiredGiB": 9.883, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:8"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 8842796317, "modelscopeLicense": "mit", "modelscopeParams": 6728625904, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 8842796317}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T12:34:49.403585+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4626360", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-04T22:53:17.234593+00:00", "modelId": "amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 44193251544, "estimatedRequiredGiB": 49.422, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 22125413673, "modelscopeLicense": "apache-2.0", "modelscopeParams": 20914757184, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:int8", "custom_tag:w8a8", "custom_tag:dynamic-quantization", "custom_tag:8-bit", "custom_tag:llm-compressor", "custom_tag:compressed-tensors", "custom_tag:zendnn", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 44221632439}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T14:46:47.882785+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4628625", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-04T22:53:17.234593+00:00", "modelId": "amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 44193251544, "estimatedRequiredGiB": 49.422, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 22125413673, "modelscopeLicense": "apache-2.0", "modelscopeParams": 20914757184, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:int8", "custom_tag:w8a8", "custom_tag:dynamic-quantization", "custom_tag:8-bit", "custom_tag:llm-compressor", "custom_tag:compressed-tensors", "custom_tag:zendnn", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 44221632439}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T14:46:47.882785+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4628625", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-04T23:04:36.601749+00:00", "modelId": "amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 44193251544, "estimatedRequiredGiB": 49.422, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "published_card_spec", "sourceUrl": "https://aclanthology.org/2025.emnlp-main.1630.pdf"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 22125413673, "modelscopeLicense": "apache-2.0", "modelscopeParams": 20914757184, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:int8", "custom_tag:w8a8", "custom_tag:dynamic-quantization", "custom_tag:8-bit", "custom_tag:llm-compressor", "custom_tag:compressed-tensors", "custom_tag:zendnn", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 44221632439}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T15:01:53.788146+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4628814", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-04T23:04:36.601749+00:00", "modelId": "amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 44193251544, "estimatedRequiredGiB": 49.422, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "published_card_spec", "sourceUrl": "https://aclanthology.org/2025.emnlp-main.1630.pdf"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 22125413673, "modelscopeLicense": "apache-2.0", "modelscopeParams": 20914757184, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:int8", "custom_tag:w8a8", "custom_tag:dynamic-quantization", "custom_tag:8-bit", "custom_tag:llm-compressor", "custom_tag:compressed-tensors", "custom_tag:zendnn", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 44221632439}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T15:01:53.788146+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4628814", "taskType": "text-generation", "verifyResult": null}
@@ -84,7 +82,6 @@
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-06T12:39:38.309054+00:00", "modelId": "groxaxo/Qwen3.8-27B-GPTQ-Pro-4bit-g64-calib128", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20034587064, "estimatedRequiredGiB": 22.413, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 20054851725, "modelscopeLicense": "apache-2.0", "modelscopeParams": 27781427952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:qwen3.8", "custom_tag:qwen3.5-architecture", "custom_tag:gptq-pro", "custom_tag:gptq", "custom_tag:4-bit", "custom_tag:4bit", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:text-generation", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "gptq", "repositoryOnDiskBytes": 20054851725}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T04:38:16.005175+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4661079", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-06T12:39:38.309054+00:00", "modelId": "groxaxo/Qwen3.8-27B-GPTQ-Pro-4bit-g64-calib128", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20034587064, "estimatedRequiredGiB": 22.413, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 20054851725, "modelscopeLicense": "apache-2.0", "modelscopeParams": 27781427952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:qwen3.8", "custom_tag:qwen3.5-architecture", "custom_tag:gptq-pro", "custom_tag:gptq", "custom_tag:4-bit", "custom_tag:4bit", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:text-generation", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "gptq", "repositoryOnDiskBytes": 20054851725}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T04:38:16.005175+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4661079", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-06T13:08:06.614723+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14289052464, "estimatedRequiredGiB": 15.972, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 14291553638, "modelscopeLicense": "mit", "modelscopeParams": 13960238080, "modelscopeTags": ["license:mit", "model_type:phi3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14291553638}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T05:06:36.493823+00:00", "targetGpu": "MetaX_c-500", "taskId": "4661437", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-06T13:08:06.614723+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14289052464, "estimatedRequiredGiB": 15.972, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 14291553638, "modelscopeLicense": "mit", "modelscopeParams": 13960238080, "modelscopeTags": ["license:mit", "model_type:phi3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14291553638}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T05:06:36.493823+00:00", "targetGpu": "MetaX_c-500", "taskId": "4661437", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-06T14:42:01.034713+00:00", "modelId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26119812080, "estimatedRequiredGiB": 29.233, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 26156887523, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:apodex", "custom_tag:arxiv:2608.23283"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26156887523}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T06:30:19.979390+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4662535", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-06T14:42:01.034713+00:00", "modelId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26119812080, "estimatedRequiredGiB": 29.233, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 26156887523, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:apodex", "custom_tag:arxiv:2608.23283"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26156887523}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T06:30:19.979390+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4662535", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-06T15:03:37.399221+00:00", "modelId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26119812080, "estimatedRequiredGiB": 29.233, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 26156887523, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:apodex", "custom_tag:arxiv:2608.23283"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26156887523}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T07:02:35.712857+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4662918", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-06T15:18:32.207677+00:00", "modelId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26119812080, "estimatedRequiredGiB": 29.233, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 26156887523, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:apodex", "custom_tag:arxiv:2608.23283"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26156887523}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T07:17:44.185498+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4663094", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-06T15:18:32.207677+00:00", "modelId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26119812080, "estimatedRequiredGiB": 29.233, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 26156887523, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:apodex", "custom_tag:arxiv:2608.23283"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26156887523}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T07:17:44.185498+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4663094", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-06T16:14:21.709544+00:00", "modelId": "empero-ai/Qwen3.8-4B-Distill", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5777, "estimatedRequiredGiB": 10.441, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9342747188, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4659865088, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:empero-ai", "custom_tag:qwen3.5", "custom_tag:qwen3.8", "custom_tag:distillation", "custom_tag:reasoning", "custom_tag:function-calling", "custom_tag:sft"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9342747188}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T08:12:14.777960+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4663715", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-06T16:14:21.709544+00:00", "modelId": "empero-ai/Qwen3.8-4B-Distill", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5777, "estimatedRequiredGiB": 10.441, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9342747188, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4659865088, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:empero-ai", "custom_tag:qwen3.5", "custom_tag:qwen3.8", "custom_tag:distillation", "custom_tag:reasoning", "custom_tag:function-calling", "custom_tag:sft"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9342747188}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T08:12:14.777960+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4663715", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-06T16:36:18.900122+00:00", "modelId": "empero-ai/Qwen3.8-4B-Distill", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5777, "estimatedRequiredGiB": 10.441, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9342747188, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4659865088, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:empero-ai", "custom_tag:qwen3.5", "custom_tag:qwen3.8", "custom_tag:distillation", "custom_tag:reasoning", "custom_tag:function-calling", "custom_tag:sft"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9342747188}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T08:34:09.456899+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4664143", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-06T16:36:18.900122+00:00", "modelId": "empero-ai/Qwen3.8-4B-Distill", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5777, "estimatedRequiredGiB": 10.441, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9342747188, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4659865088, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:empero-ai", "custom_tag:qwen3.5", "custom_tag:qwen3.8", "custom_tag:distillation", "custom_tag:reasoning", "custom_tag:function-calling", "custom_tag:sft"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9342747188}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T08:34:09.456899+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4664143", "taskType": "text-generation", "verifyResult": null}