state: generation 11637 (intent)

This commit is contained in:
2026-09-21 19:21:50 +00:00
parent 6160213592
commit d9c1dd0e50
7 changed files with 92 additions and 72 deletions

View File

@@ -2768,7 +2768,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-21T19:17:36.123466+00:00",
"generatedAt": "2026-09-21T19:21:35.741313+00:00",
"summary": {
"activeBlockCount": 139,
"byGpuFramework": {

View File

@@ -434,7 +434,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-21T19:20:20.489628+00:00",
"generatedAt": "2026-09-21T19:21:49.492289+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,

View File

@@ -1,5 +1,5 @@
{
"catalogUpdatedAt": "2026-09-21T19:20:20.489628+00:00",
"catalogUpdatedAt": "2026-09-21T19:21:49.492289+00:00",
"configuredTaskTypes": [
"text-generation"
],
@@ -56,7 +56,7 @@
"time-series-forecasting"
],
"errors": [],
"generatedAt": "2026-09-21T19:20:29.177750+00:00",
"generatedAt": "2026-09-21T19:21:49.854724+00:00",
"gpuCatalog": {
"Ascend_910-b3": {
"canVerify": true,
@@ -402,18 +402,6 @@
],
"updatedAt": "2026-09-21T19:05:29.405003+00:00"
},
"https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Instruct-GGUF|2026-08-26T17:45:33+00:00|Biren_166m": {
"taskTypes": [
"text-generation"
],
"updatedAt": "2026-09-21T18:49:51.256932+00:00"
},
"https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Instruct-GGUF|2026-08-26T17:45:33+00:00|Cambricon_mlu-370-x8": {
"taskTypes": [
"text-generation"
],
"updatedAt": "2026-09-21T18:49:51.224362+00:00"
},
"https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Instruct-GGUF|2026-08-26T17:45:33+00:00|Iluvatar_mrv-100": {
"taskTypes": [
"text-generation"
@@ -1999,12 +1987,6 @@
],
"updatedAt": "2026-09-21T18:49:54.378616+00:00"
},
"https://modelscope.cn/models/aisingapore/Llama-SEA-LION-v3-8B|2026-08-26T17:38:05+00:00|Mthreads_s4000": {
"taskTypes": [
"text-generation"
],
"updatedAt": "2026-09-21T18:49:50.958318+00:00"
},
"https://modelscope.cn/models/aisingapore/Llama-SEA-LION-v3.5-70B-R-NVFP4|2026-08-26T15:57:06+00:00|Ascend_910-b3": {
"taskTypes": [
"text-generation",
@@ -5692,6 +5674,20 @@
],
"updatedAt": "2026-09-21T19:05:15.902078+00:00"
},
"https://modelscope.cn/models/prithivMLmods/Qwen-Image-2.1-PE-T2I-MLX|2026-09-21T18:49:30+00:00|Biren_166m": {
"taskTypes": [
"text-generation"
],
"updatedAt": "2026-09-21T19:21:49.801875+00:00"
},
"https://modelscope.cn/models/prithivMLmods/Qwen-Image-2.1-PE-T2I-MLX|2026-09-21T18:49:30+00:00|Cambricon_mlu-370-x8": {
"taskTypes": [
"text-generation",
"text-to-image-generation",
"visual-multi-modal"
],
"updatedAt": "2026-09-21T19:21:49.755436+00:00"
},
"https://modelscope.cn/models/prithivMLmods/Qwen-Image-2.1-PE-T2I-MLX|2026-09-21T18:49:30+00:00|Iluvatar_bi-150": {
"taskTypes": [
"asr",
@@ -5726,6 +5722,14 @@
],
"updatedAt": "2026-09-21T19:05:15.849513+00:00"
},
"https://modelscope.cn/models/prithivMLmods/Qwen-Image-2.1-PE-T2I-MLX|2026-09-21T18:49:30+00:00|hygon_k100-ai": {
"taskTypes": [
"text-generation",
"text-to-image-generation",
"visual-multi-modal"
],
"updatedAt": "2026-09-21T19:21:49.854724+00:00"
},
"https://modelscope.cn/models/rengensheng/Ternary-Bonsai-2-27B-gguf|2026-09-18T03:00:42+00:00|Biren_166m": {
"taskTypes": [
"text-generation"
@@ -6896,6 +6900,6 @@
"updateTime": "2025-12-22 08:59:53"
}
],
"taskTreeUpdatedAt": "2026-09-21T19:20:20.489628+00:00",
"taskTreeUpdatedAt": "2026-09-21T19:21:49.492289+00:00",
"version": 1
}

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-21T19:17:36.046225+00:00",
"lastSyncTime": "2026-09-21T19:17:35.577982+00:00",
"generatedAt": "2026-09-21T19:21:35.669232+00:00",
"lastSyncTime": "2026-09-21T19:21:35.063209+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -3102,7 +3102,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 204,
"failureBreakdown": {
"ambiguous_runtime": 108,
"ambiguous_runtime": 109,
"context_length": 1,
"framework_architecture_unsupported": 155,
"memory_capacity": 10,
@@ -3110,7 +3110,7 @@
"repository_structure": 27,
"tokenizer_compatibility": 11
},
"failureCount": 313,
"failureCount": 314,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -3120,8 +3120,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 313,
"unresolvedFailureCount": 108
"total": 314,
"unresolvedFailureCount": 109
},
"Biren_166m|unknown|feature_emb": {
"attributableFailureCount": 0,
@@ -5426,7 +5426,7 @@
"decisionSuccessRate": 0.0242,
"decisionTotal": 3629,
"failureBreakdown": {
"ambiguous_runtime": 1495,
"ambiguous_runtime": 1496,
"architecture_compatibility": 112,
"attention_backend": 1,
"backend_operator": 84,
@@ -5440,15 +5440,15 @@
"tokenizer_compatibility": 412,
"参数/模板问题": 46
},
"failureCount": 5947,
"failureCount": 5948,
"failureRate": 0.9854,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 865,
"successCount": 88,
"successRate": 0.0146,
"total": 6035,
"unresolvedFailureCount": 1541
"total": 6036,
"unresolvedFailureCount": 1542
},
"vllm-customized": {
"attributableFailureCount": 6,
@@ -5594,7 +5594,7 @@
"unresolvedFailureCount": 104
}
},
"generatedAt": "2026-09-21T19:17:36.034836+00:00",
"generatedAt": "2026-09-21T19:21:35.657452+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 99,
@@ -5628,7 +5628,7 @@
"decisionSuccessRate": 0.1636,
"decisionTotal": 385,
"failureBreakdown": {
"ambiguous_runtime": 177,
"ambiguous_runtime": 178,
"context_length": 1,
"framework_architecture_unsupported": 178,
"memory_capacity": 19,
@@ -5640,15 +5640,15 @@
"日志缺失": 14,
"验证失败": 175
},
"failureCount": 958,
"failureRate": 0.9383,
"failureCount": 959,
"failureRate": 0.9384,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 63,
"successRate": 0.0617,
"total": 1021,
"unresolvedFailureCount": 634
"successRate": 0.0616,
"total": 1022,
"unresolvedFailureCount": 635
},
"Biren_166m": {
"attributableFailureCount": 186,
@@ -7783,9 +7783,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 3
"ambiguous_runtime": 4
},
"failureCount": 3,
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "llama",
@@ -7797,8 +7797,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 3,
"unresolvedFailureCount": 3
"total": 4,
"unresolvedFailureCount": 4
},
"Ascend_910-b4|vllm|text-generation|llama|none": {
"attributableFailureCount": 1,
@@ -23913,9 +23913,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 32,
@@ -23928,8 +23928,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Ascend_910-b4|vllm|text-generation|llama|awq|33": {
"attributableFailureCount": 0,
@@ -37355,15 +37355,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 16373,
"totalRecords": 16567,
"terminalRecords": 16374,
"totalRecords": 16568,
"totals": {
"attributableFailureCount": 5908,
"decisionFailureRate": 0.862,
"decisionSuccessRate": 0.138,
"decisionTotal": 6854,
"failureBreakdown": {
"ambiguous_runtime": 4010,
"ambiguous_runtime": 4011,
"architecture_compatibility": 212,
"attention_backend": 1,
"backend_operator": 104,
@@ -37379,31 +37379,31 @@
"日志缺失": 719,
"验证失败": 674
},
"failureCount": 15427,
"failureCount": 15428,
"failureRate": 0.9422,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 925,
"successCount": 946,
"successRate": 0.0578,
"total": 16373,
"unresolvedFailureCount": 8594
"total": 16374,
"unresolvedFailureCount": 8595
},
"warnings": [
"GPU Iluvatar_mrv-100 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 Cambricon_mlu-370-x8 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Kunlunxin_p-800 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 Biren_166m 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Iluvatar_bi-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 Ascend_910-b3 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 Iluvatar_bi-150 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 hygon_k100-ai 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 MetaX_c-500 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。",
"组合 Iluvatar_bi-150|vllm|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 Sunrise_pt-200-x1|vllm_fix_tokenizer|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。",
@@ -37443,6 +37443,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 16567,
"summarizedRecords": 16568,
"version": 1
}

View File

@@ -2243,6 +2243,23 @@
{"batchId": "5269978ec6ff4d4685f0f39b692d2f1b", "completedAt": "2026-09-21T19:05:51.875616+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:05:38.446408+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d0ca412c123641719dacb7dfb97b63da", "lastModified": "2026-09-21T18:48:50+00:00", "modelAddress": "https://modelscope.cn/models/prithivMLmods/Nexus-9B-CodeCore-Merge", "reason": null, "reconciledAt": "2026-09-21T19:17:49.511099+00:00", "repoId": "prithivMLmods/Nexus-9B-CodeCore-Merge", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "5006056", "taskType": "text-generation"}
{"batchId": "5269978ec6ff4d4685f0f39b692d2f1b", "completedAt": "2026-09-21T19:05:51.875619+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:05:38.446450+00:00", "framework": "vllm_fix_tokenizer", "intentId": "7753717bc25a43beb5ca668daca2bc8f", "lastModified": "2026-09-21T18:28:31+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g8-v2_C", "reason": null, "reconciledAt": "2026-09-21T19:17:49.510876+00:00", "repoId": "nkkbr/Mini-K3-1H-decay-g8-v2_C", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "5006047", "taskType": "text-generation"}
{"batchId": "5269978ec6ff4d4685f0f39b692d2f1b", "completedAt": "2026-09-21T19:05:51.875622+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:05:38.446492+00:00", "framework": "vllm_fix_tokenizer", "intentId": "76de0c84d4634e4da02c0231c9f1d15c", "lastModified": "2026-09-21T18:49:30+00:00", "modelAddress": "https://modelscope.cn/models/prithivMLmods/Qwen-Image-2.1-PE-T2I-MLX", "reason": null, "reconciledAt": "2026-09-21T19:17:49.509000+00:00", "repoId": "prithivMLmods/Qwen-Image-2.1-PE-T2I-MLX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "5006057", "taskType": "text-generation"}
{"batchId": "bb1305e1ec154c0a878be3ad3593b296", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:21:50.577959+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c94917cabce24c94b5eab5974b9a548f", "lastModified": "2026-09-21T18:44:33+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attnres-block6-v1_C", "repoId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "bb1305e1ec154c0a878be3ad3593b296", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:21:50.578066+00:00", "framework": "vllm_fix_tokenizer", "intentId": "071ba1f04adf4b698baef6577f0be575", "lastModified": "2026-09-21T18:38:06+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attnres-standard-v1_B", "repoId": "nkkbr/Mini-K3-1H-attnres-standard-v1_B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "bb1305e1ec154c0a878be3ad3593b296", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:21:50.578113+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d3100f5726d04987b7134e0cc4e06cdf", "lastModified": "2026-09-21T18:45:44+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g16-v2_B", "repoId": "nkkbr/Mini-K3-1H-decay-g16-v2_B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "bb1305e1ec154c0a878be3ad3593b296", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:21:50.578157+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8153d28c2c6941bcb9cc07db9b20db4d", "lastModified": "2026-09-21T18:43:38+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g2-v2_C", "repoId": "nkkbr/Mini-K3-1H-decay-g2-v2_C", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "bb1305e1ec154c0a878be3ad3593b296", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:21:50.578201+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a617bdd5951c4a31bdcf6cbc419a2d23", "lastModified": "2026-09-21T18:42:39+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "repoId": "nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "bb1305e1ec154c0a878be3ad3593b296", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:21:50.578244+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a7c7eaf4be5c4a1686897033525620d3", "lastModified": "2026-09-21T18:39:37+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-mamba2-n64-g8-v1_C", "repoId": "nkkbr/Mini-K3-1H-mamba2-n64-g8-v1_C", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "bb1305e1ec154c0a878be3ad3593b296", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:21:50.578287+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5b7f93be510a44f5853e3ba22e464bf3", "lastModified": "2026-09-21T18:24:38+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attnres-block2-v1_B", "repoId": "nkkbr/Mini-K3-1H-attnres-block2-v1_B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "bb1305e1ec154c0a878be3ad3593b296", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:21:50.578327+00:00", "framework": "vllm_tokenizer_patch", "intentId": "50b2c21c940c4a1f91e3303c36ab1d6b", "lastModified": "2026-09-21T18:27:54+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g1-v2_B", "repoId": "nkkbr/Mini-K3-1H-decay-g1-v2_B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "bb1305e1ec154c0a878be3ad3593b296", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:21:50.578366+00:00", "framework": "vllm_tokenizer_patch", "intentId": "342695078f384063a6284a0d0018f374", "lastModified": "2026-09-21T18:27:55+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g32-v2_C", "repoId": "nkkbr/Mini-K3-1H-decay-g32-v2_C", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "bb1305e1ec154c0a878be3ad3593b296", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:21:50.578403+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a2b50e6a72ef4a389713d42a4e56832c", "lastModified": "2026-09-21T18:24:35+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g4-v2_B", "repoId": "nkkbr/Mini-K3-1H-decay-g4-v2_B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "bb1305e1ec154c0a878be3ad3593b296", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:21:50.578441+00:00", "framework": "vllm_tokenizer_patch", "intentId": "fd077195c8124952b8312d54ede6409d", "lastModified": "2026-09-21T18:32:18+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g64-v2_B", "repoId": "nkkbr/Mini-K3-1H-decay-g64-v2_B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "bb1305e1ec154c0a878be3ad3593b296", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:21:50.578479+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c1308376f1784b7fb89ff8095a3c0a6d", "lastModified": "2026-09-21T18:34:41+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-kda-kernel-32-v2_D", "repoId": "nkkbr/Mini-K3-1H-kda-kernel-32-v2_D", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "bb1305e1ec154c0a878be3ad3593b296", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:21:50.578516+00:00", "framework": "vllm_tokenizer_patch", "intentId": "b96e54632a0e4cf4b654c89f78f34e36", "lastModified": "2026-09-21T18:33:37+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-kda-kernel-8-v2_D", "repoId": "nkkbr/Mini-K3-1H-kda-kernel-8-v2_D", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "bb1305e1ec154c0a878be3ad3593b296", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:21:50.578552+00:00", "framework": "vllm_tokenizer_patch", "intentId": "56413781871444c4933c5a8ef5437185", "lastModified": "2026-09-21T18:24:35+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-mamba2-n64-g4-v1_B", "repoId": "nkkbr/Mini-K3-1H-mamba2-n64-g4-v1_B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "bb1305e1ec154c0a878be3ad3593b296", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:21:50.578590+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e3c7d48dfbd8477eafea650e1a6c9d4f", "lastModified": "2026-09-21T18:28:31+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g8-v2_C", "repoId": "nkkbr/Mini-K3-1H-decay-g8-v2_C", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "bb1305e1ec154c0a878be3ad3593b296", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:21:50.578628+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b7e6b05cb9ba491390415f227d1728c9", "lastModified": "2026-09-21T18:49:30+00:00", "modelAddress": "https://modelscope.cn/models/prithivMLmods/Qwen-Image-2.1-PE-T2I-MLX", "repoId": "prithivMLmods/Qwen-Image-2.1-PE-T2I-MLX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
{"batchId": "bb1305e1ec154c0a878be3ad3593b296", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:21:50.578686+00:00", "framework": "vllm_fix_tokenizer", "intentId": "43ef82c63f4a48a2bca613b7a3c0ae3a", "lastModified": "2026-09-21T18:48:50+00:00", "modelAddress": "https://modelscope.cn/models/prithivMLmods/Nexus-9B-CodeCore-Merge", "repoId": "prithivMLmods/Nexus-9B-CodeCore-Merge", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "f8d3f1991720478ea905a5ecf7d43601", "completedAt": "2026-09-21T19:05:00.691781+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:00:55.137064+00:00", "framework": "vllm", "intentId": "64b834dd640742a0b32535bde02b94ad", "repoId": "CohereLabs/tiny-aya-base-32K", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8d3f1991720478ea905a5ecf7d43601", "completedAt": "2026-09-21T19:05:00.691779+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:00:55.137007+00:00", "framework": "vllm", "intentId": "d6229ef4ac9942078baa35e312133d9d", "repoId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8d3f1991720478ea905a5ecf7d43601", "completedAt": "2026-09-21T19:05:00.691776+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:00:55.136949+00:00", "framework": "vllm", "intentId": "cff6b666a842431faf928f94c2086fdf", "repoId": "nm-testing/llama-3-instruct-w8a8-dyn-per-token-test", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"}

View File

@@ -2,24 +2,24 @@
"agentVersion": "2026.09.20.2",
"checksums": {
".modelhub_state/account_capacity.json": "68d2a8390ad022f2ddcd30841f3860c4535387fa64cb46dc7507eb16837e798f",
".modelhub_state/architecture_compatibility_blacklist.json": "9733bfe74ff14da66e3799b6df519ff24932f2d97ac4bcfc4472d9f83e479e47",
".modelhub_state/architecture_compatibility_blacklist.json": "3d1a145e43773b7a71c0a379908274f3eb3e2faacda0b85b672da16717d3883e",
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
".modelhub_state/market_intelligence.json": "7f278261cacc6daed799c978ba7b276a6ec3c833496b424dde8f52498a5bf33b",
".modelhub_state/official_capabilities.json": "4a655b999ef0f88538892e1c159c666388a90e8cbb4795de393bbbaa6a963c8c",
".modelhub_state/outcome_checkpoint.json": "b5821a07cebe1a7b70929b4b0bdaefba19779df21f432727fdb89f367f4633ab",
".modelhub_state/market_intelligence.json": "6fa822a38b2ad051db10ab4199b04a1bf7b363b821f0b47e2d3816f4f540244e",
".modelhub_state/official_capabilities.json": "3600e4227b0b6c10724a15fd19e8b524be37d1affa577f986472f00eeaa40ebf",
".modelhub_state/outcome_checkpoint.json": "3bbfea2fa7af18a3eb68f75184c134bccd95915bda580570fdfdf8adb5c8cbf9",
".modelhub_state/queue_cleanup_latest.json": "fab470f2bbf8c39d73c8917d9fdab78c775c47a597aa2530a529e5a7ae55d4ec",
".modelhub_state/recent_outcomes.jsonl": "a62acfa64b4e7602c68217fdee9fa27df4649fbdb548e1da00eebd92efff142e",
".modelhub_state/recovery_active_tasks.jsonl": "7b1bc073f2f0bdb28d304855e20e2177f43918b5ef10655d67367a5a8702874c",
".modelhub_state/recovery_intents.jsonl": "e7056126965ae8deb682cae47a3022190620008eca0a22a47257c6d7375a31f7",
".modelhub_state/recovery_intents.jsonl": "875829333b3246e5ad28471934844e469461c98ec374845ee5a5389a442a2384",
".modelhub_state/routing_intelligence.json": "463dab8d5a4747cc8a868b78b02943715349067a1342e1ad01ece306c3d38e77",
".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989",
".modelhub_state/worker_crashes.jsonl": "07505b69e0b050da5f90f8b046a3069d3e1ca2574ca39896bc7d8a66293167f7",
"ledger/submissions.jsonl": "4416ab2366ff2d2285de231c63c989626a88bf2540f5fa7661aeefa313de6e81",
"outcomes/submissions.jsonl": "f0a7b91e04661667816663fb422db1a7a9515ef4672999e57111bada114bf31b"
"outcomes/submissions.jsonl": "7e4f447349a233eed1891042ff322d6876b975e774c8cd1a03fab80e22fa4ff4"
},
"generation": 11636,
"phase": "cycle",
"generation": 11637,
"phase": "intent",
"schemaVersion": 1,
"updatedAt": "2026-09-21T19:20:33.224781+00:00",
"updatedAt": "2026-09-21T19:21:50.732812+00:00",
"writerId": "8b35139af6674067a339a670222d4b67"
}

View File

@@ -461,7 +461,6 @@
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:30:54.600320+00:00", "modelId": "sbintuitions/sarashina2.2-3b-instruct-v0.1", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6711252896, "estimatedRequiredGiB": 7.503, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 6713123803, "modelscopeLicense": "mit", "modelscopeParams": 3355609600, "modelscopeTags": ["license:mit", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6713123803}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:30:23.758933+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4969807", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:30:54.599773+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 54864980000, "estimatedRequiredGiB": 61.361, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 54904930780, "modelscopeLicense": "gemma", "modelscopeParams": 27432406640, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 54904930780}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:30:23.763321+00:00", "targetGpu": "MetaX_c-500", "taskId": "4969808", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:30:54.600313+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727938576, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "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": "2026-09-20T03:30:31.137775+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969811", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:30:54.600377+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "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": "2026-09-20T03:30:31.143975+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969815", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:30:54.600145+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737318602, "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": 5737318602}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:30:31.135514+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969816", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:30:54.599690+00:00", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8447876488, "estimatedRequiredGiB": 9.452, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "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": "2026-09-20T03:30:31.146899+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969812", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-20T12:01:00.671231+00:00", "modelId": "neuralmagic/Meta-Llama-3-8B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084013360, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093325202, "modelscopeLicense": "llama3", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093325202}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:40:37.351352+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969964", "taskType": "text-generation", "verifyResult": null}
@@ -1002,10 +1001,10 @@
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T19:05:56.949020+00:00", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "modelProfile": {"architectures": ["MuseGlimmerForConditionalGeneration"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21407235494, "estimatedRequiredGiB": 23.956, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "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": "2026-09-21T11:00:43.861933+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4999589", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T19:10:15.559190+00:00", "modelId": "neuralmagic/Meta-Llama-3-8B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084013360, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093325202, "modelscopeLicense": "llama3", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093325202}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T11:07:40.941920+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4999639", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T19:13:53.564409+00:00", "modelId": "neuralmagic/SmolLM-135M-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "382ef635ba042d77a729681df1994f5ac5e7beaf5980ac5d2e7045645d11c732", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 219850592, "estimatedRequiredGiB": 0.249, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 223236742, "modelscopeLicense": "apache-2.0", "modelscopeParams": 162826560, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 223236742}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T11:10:31.847181+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4999689", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4020365960, "estimatedRequiredGiB": 4.496, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 4022810352, "modelscopeLicense": "mit", "modelscopeParams": 3821079552, "modelscopeTags": ["license:mit", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4022810352}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T11:18:21.951854+00:00", "targetGpu": "Vastai_va16", "taskId": "4999763", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084040952, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093261800, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": {"ambiguous_runtime": 1, "context_length": 1}, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-09-21T10:33:30.477761+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 9093261800}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T11:18:21.958399+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4999764", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "modelProfile": {"architectures": ["Phi3SmallForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8630134648, "estimatedRequiredGiB": 9.647, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3small", "modelscopeFileSize": 8632060880, "modelscopeLicense": "mit", "modelscopeParams": 7803314176, "modelscopeTags": ["license:mit", "model_type:phi3small", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8632060880}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T11:18:21.960935+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4999762", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-8BIT", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 34327989512, "estimatedRequiredGiB": 38.385, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 34346039951, "modelscopeLicense": "mit", "modelscopeParams": 32762123264, "modelscopeTags": ["license:mit", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 34346039951}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T11:18:21.963694+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4999765", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T19:21:35.063154+00:00", "modelId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4020365960, "estimatedRequiredGiB": 4.496, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 4022810352, "modelscopeLicense": "mit", "modelscopeParams": 3821079552, "modelscopeTags": ["license:mit", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4022810352}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T11:18:21.951854+00:00", "targetGpu": "Vastai_va16", "taskId": "4999763", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T19:21:35.063199+00:00", "modelId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084040952, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093261800, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": {"ambiguous_runtime": 1, "context_length": 1}, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-09-21T10:33:30.477761+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 9093261800}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T11:18:21.958399+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4999764", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T19:21:35.063181+00:00", "modelId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "modelProfile": {"architectures": ["Phi3SmallForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8630134648, "estimatedRequiredGiB": 9.647, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3small", "modelscopeFileSize": 8632060880, "modelscopeLicense": "mit", "modelscopeParams": 7803314176, "modelscopeTags": ["license:mit", "model_type:phi3small", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8632060880}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T11:18:21.960935+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4999762", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T19:21:35.063192+00:00", "modelId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-8BIT", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 34327989512, "estimatedRequiredGiB": 38.385, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 34346039951, "modelscopeLicense": "mit", "modelscopeParams": 32762123264, "modelscopeTags": ["license:mit", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 34346039951}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T11:18:21.963694+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4999765", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "RedHatAI/Phi-3-mini-128k-instruct-FP8", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4018332584, "estimatedRequiredGiB": 4.494, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 4020783717, "modelscopeLicense": "mit", "modelscopeParams": 3821079552, "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": 4020783717}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T11:40:35.034782+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5000088", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "JANGQ-AI/Ling-2.6-flash-JANGTQ", "modelProfile": {"architectures": ["BailingMoeV2_5ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30593642304, "estimatedRequiredGiB": 34.208, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bailing_hybrid", "modelscopeFileSize": 30608423891, "modelscopeLicense": "mit", "modelscopeParams": null, "modelscopeTags": ["license:mit", "model_type:bailing_hybrid", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:mixture-of-experts", "custom_tag:hybrid-attention", "custom_tag:mla", "custom_tag:lightning-attention", "custom_tag:jangtq", "custom_tag:jangq-ai", "custom_tag:mlx", "custom_tag:bailing", "custom_tag:ling", "custom_tag:apple-silicon"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 30608423891}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T11:40:34.995530+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5000087", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "webAI-Official/TwIL-LM3", "modelProfile": {"architectures": ["SmolLM3ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6150235096, "estimatedRequiredGiB": 24.879, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "smollm3", "modelscopeFileSize": 22261451381, "modelscopeLicense": "other", "modelscopeParams": 3075098624, "modelscopeTags": ["license:other", "model_type:smollm3", "library:pytorch", "library:transformer", "library:lora", "library:safetensors", "library:gguf", "task:text-generation", "custom_tag:formal-logic", "custom_tag:reasoning", "custom_tag:lora", "custom_tag:model-merging", "custom_tag:wise-ft", "custom_tag:reinforcement-learning", "custom_tag:grpo", "custom_tag:smollm3", "custom_tag:twil-lm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22261451381}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T11:40:35.004115+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5000089", "taskType": "text-generation", "verifyResult": null}