state: generation 11594 (intent)
This commit is contained in:
@@ -2751,7 +2751,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-21T17:41:29.227970+00:00",
|
||||
"generatedAt": "2026-09-21T18:00:40.567909+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 138,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -434,7 +434,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-21T17:59:11.671356+00:00",
|
||||
"generatedAt": "2026-09-21T18:00:51.251296+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-21T17:41:29.155215+00:00",
|
||||
"lastSyncTime": "2026-09-21T17:41:26.757156+00:00",
|
||||
"generatedAt": "2026-09-21T18:00:40.490817+00:00",
|
||||
"lastSyncTime": "2026-09-21T18:00:38.063699+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -3055,18 +3055,18 @@
|
||||
"unresolvedFailureCount": 17
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation": {
|
||||
"attributableFailureCount": 23,
|
||||
"attributableFailureCount": 24,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 23,
|
||||
"decisionTotal": 24,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 38,
|
||||
"framework_architecture_unsupported": 22,
|
||||
"ambiguous_runtime": 39,
|
||||
"framework_architecture_unsupported": 23,
|
||||
"platform_infrastructure": 1,
|
||||
"repository_structure": 1,
|
||||
"参数/模板问题": 6
|
||||
},
|
||||
"failureCount": 68,
|
||||
"failureCount": 70,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"pendingCount": 0,
|
||||
@@ -3076,24 +3076,24 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 68,
|
||||
"unresolvedFailureCount": 44
|
||||
"total": 70,
|
||||
"unresolvedFailureCount": 45
|
||||
},
|
||||
"Ascend_910-b4|vllm|text-generation": {
|
||||
"attributableFailureCount": 201,
|
||||
"attributableFailureCount": 203,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 201,
|
||||
"decisionTotal": 203,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 105,
|
||||
"context_length": 1,
|
||||
"framework_architecture_unsupported": 154,
|
||||
"memory_capacity": 9,
|
||||
"framework_architecture_unsupported": 155,
|
||||
"memory_capacity": 10,
|
||||
"platform_infrastructure": 1,
|
||||
"repository_structure": 27,
|
||||
"tokenizer_compatibility": 10
|
||||
},
|
||||
"failureCount": 307,
|
||||
"failureCount": 309,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
@@ -3103,7 +3103,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 307,
|
||||
"total": 309,
|
||||
"unresolvedFailureCount": 105
|
||||
},
|
||||
"Biren_166m|unknown|feature_emb": {
|
||||
@@ -5404,18 +5404,18 @@
|
||||
"unresolvedFailureCount": 6446
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 3535,
|
||||
"attributableFailureCount": 3537,
|
||||
"decisionFailureRate": 0.9757,
|
||||
"decisionSuccessRate": 0.0243,
|
||||
"decisionTotal": 3623,
|
||||
"decisionTotal": 3625,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1492,
|
||||
"architecture_compatibility": 112,
|
||||
"attention_backend": 1,
|
||||
"backend_operator": 84,
|
||||
"context_length": 161,
|
||||
"framework_architecture_unsupported": 1304,
|
||||
"memory_capacity": 721,
|
||||
"framework_architecture_unsupported": 1305,
|
||||
"memory_capacity": 722,
|
||||
"model_load": 207,
|
||||
"platform_infrastructure": 865,
|
||||
"repository_structure": 470,
|
||||
@@ -5423,14 +5423,14 @@
|
||||
"tokenizer_compatibility": 411,
|
||||
"参数/模板问题": 45
|
||||
},
|
||||
"failureCount": 5937,
|
||||
"failureCount": 5939,
|
||||
"failureRate": 0.9854,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 865,
|
||||
"successCount": 88,
|
||||
"successRate": 0.0146,
|
||||
"total": 6025,
|
||||
"total": 6027,
|
||||
"unresolvedFailureCount": 1537
|
||||
},
|
||||
"vllm-customized": {
|
||||
@@ -5550,15 +5550,15 @@
|
||||
"unresolvedFailureCount": 196
|
||||
},
|
||||
"vllm_tokenizer_patch": {
|
||||
"attributableFailureCount": 73,
|
||||
"decisionFailureRate": 0.9733,
|
||||
"decisionSuccessRate": 0.0267,
|
||||
"decisionTotal": 75,
|
||||
"attributableFailureCount": 74,
|
||||
"decisionFailureRate": 0.9737,
|
||||
"decisionSuccessRate": 0.0263,
|
||||
"decisionTotal": 76,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 70,
|
||||
"ambiguous_runtime": 71,
|
||||
"backend_operator": 1,
|
||||
"context_length": 3,
|
||||
"framework_architecture_unsupported": 62,
|
||||
"framework_architecture_unsupported": 63,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 2,
|
||||
"platform_infrastructure": 1,
|
||||
@@ -5566,18 +5566,18 @@
|
||||
"tokenizer_compatibility": 1,
|
||||
"参数/模板问题": 27
|
||||
},
|
||||
"failureCount": 171,
|
||||
"failureRate": 0.9884,
|
||||
"failureCount": 173,
|
||||
"failureRate": 0.9886,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 2,
|
||||
"successRate": 0.0116,
|
||||
"total": 173,
|
||||
"unresolvedFailureCount": 97
|
||||
"successRate": 0.0114,
|
||||
"total": 175,
|
||||
"unresolvedFailureCount": 98
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-21T17:41:29.141921+00:00",
|
||||
"generatedAt": "2026-09-21T18:00:40.479875+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 99,
|
||||
@@ -5606,15 +5606,15 @@
|
||||
"unresolvedFailureCount": 161
|
||||
},
|
||||
"Ascend_910-b4": {
|
||||
"attributableFailureCount": 318,
|
||||
"decisionFailureRate": 0.8346,
|
||||
"decisionSuccessRate": 0.1654,
|
||||
"decisionTotal": 381,
|
||||
"attributableFailureCount": 321,
|
||||
"decisionFailureRate": 0.8359,
|
||||
"decisionSuccessRate": 0.1641,
|
||||
"decisionTotal": 384,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 170,
|
||||
"ambiguous_runtime": 171,
|
||||
"context_length": 1,
|
||||
"framework_architecture_unsupported": 176,
|
||||
"memory_capacity": 18,
|
||||
"framework_architecture_unsupported": 178,
|
||||
"memory_capacity": 19,
|
||||
"model_load": 85,
|
||||
"platform_infrastructure": 2,
|
||||
"repository_structure": 28,
|
||||
@@ -5623,15 +5623,15 @@
|
||||
"日志缺失": 14,
|
||||
"验证失败": 175
|
||||
},
|
||||
"failureCount": 947,
|
||||
"failureRate": 0.9376,
|
||||
"failureCount": 951,
|
||||
"failureRate": 0.9379,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 2,
|
||||
"successCount": 63,
|
||||
"successRate": 0.0624,
|
||||
"total": 1010,
|
||||
"unresolvedFailureCount": 627
|
||||
"successRate": 0.0621,
|
||||
"total": 1014,
|
||||
"unresolvedFailureCount": 628
|
||||
},
|
||||
"Biren_166m": {
|
||||
"attributableFailureCount": 184,
|
||||
@@ -7137,6 +7137,29 @@
|
||||
"total": 4,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|lfm2_moe|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"modelType": "lfm2_moe",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|lfm2|none": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -7189,9 +7212,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4
|
||||
"ambiguous_runtime": 5
|
||||
},
|
||||
"failureCount": 4,
|
||||
"failureCount": 5,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"modelType": "llama",
|
||||
@@ -7203,8 +7226,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 4,
|
||||
"unresolvedFailureCount": 4
|
||||
"total": 5,
|
||||
"unresolvedFailureCount": 5
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|llama|none": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -7668,6 +7691,29 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b4|vllm|text-generation|bailing_hybrid|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"memory_capacity": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"modelType": "bailing_hybrid",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b4|vllm|text-generation|llama|awq": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -7714,6 +7760,29 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b4|vllm|text-generation|muse_glimmer|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"modelType": "muse_glimmer",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b4|vllm|text-generation|qwen3_vl|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -22485,6 +22554,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|lfm2_moe|none|33": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"loadSizeLog2Bucket": 33,
|
||||
"modelType": "lfm2_moe",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|lfm2|none|29": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -22707,9 +22800,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
"ambiguous_runtime": 2
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureCount": 2,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"loadSizeLog2Bucket": 33,
|
||||
@@ -22722,8 +22815,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 2
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|llama|none|30": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -23397,6 +23490,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b4|vllm|text-generation|bailing_hybrid|none|33": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"memory_capacity": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"loadSizeLog2Bucket": 33,
|
||||
"modelType": "bailing_hybrid",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b4|vllm|text-generation|llama|awq|30": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -23469,6 +23586,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b4|vllm|text-generation|muse_glimmer|none|34": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"loadSizeLog2Bucket": 34,
|
||||
"modelType": "muse_glimmer",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b4|vllm|text-generation|qwen3_vl|none|34": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -36557,21 +36698,21 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 16345,
|
||||
"totalRecords": 16539,
|
||||
"terminalRecords": 16349,
|
||||
"totalRecords": 16543,
|
||||
"totals": {
|
||||
"attributableFailureCount": 5900,
|
||||
"decisionFailureRate": 0.8618,
|
||||
"decisionSuccessRate": 0.1382,
|
||||
"decisionTotal": 6846,
|
||||
"attributableFailureCount": 5903,
|
||||
"decisionFailureRate": 0.8619,
|
||||
"decisionSuccessRate": 0.1381,
|
||||
"decisionTotal": 6849,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 3991,
|
||||
"ambiguous_runtime": 3992,
|
||||
"architecture_compatibility": 212,
|
||||
"attention_backend": 1,
|
||||
"backend_operator": 103,
|
||||
"context_length": 321,
|
||||
"framework_architecture_unsupported": 2081,
|
||||
"memory_capacity": 1198,
|
||||
"framework_architecture_unsupported": 2083,
|
||||
"memory_capacity": 1199,
|
||||
"model_load": 499,
|
||||
"platform_infrastructure": 925,
|
||||
"repository_structure": 739,
|
||||
@@ -36581,31 +36722,31 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 674
|
||||
},
|
||||
"failureCount": 15399,
|
||||
"failureCount": 15403,
|
||||
"failureRate": 0.9421,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 925,
|
||||
"successCount": 946,
|
||||
"successRate": 0.0579,
|
||||
"total": 16345,
|
||||
"unresolvedFailureCount": 8574
|
||||
"total": 16349,
|
||||
"unresolvedFailureCount": 8575
|
||||
},
|
||||
"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 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。",
|
||||
"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。",
|
||||
@@ -36645,6 +36786,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 16539,
|
||||
"summarizedRecords": 16543,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -2190,6 +2190,67 @@
|
||||
{"batchId": "72cb9a4a00eb4f81aa0d838e048a300f", "completedAt": "2026-09-21T17:59:07.220187+00:00", "configFingerprint": "58bd440e460cf3e4d9271b3c32c451e80254e59faf47ce55dcda11588cf4117e", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:54:45.272288+00:00", "framework": "vllm", "intentId": "c29a84b01fbd4ee6af79550df0a097f8", "lastModified": "2026-08-24T18:24:11+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2", "reason": null, "reconciledAt": "2026-09-21T17:59:08.869520+00:00", "repoId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "recovered_active", "targetGpu": "Mthreads_s4000", "taskId": "5005091", "taskType": "text-generation"}
|
||||
{"batchId": "72cb9a4a00eb4f81aa0d838e048a300f", "completedAt": "2026-09-21T17:59:07.220190+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:54:45.272346+00:00", "framework": "vllm", "intentId": "439fc9c1e671466b944c30d87b849d94", "lastModified": "2026-08-24T17:55:20+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-W8A8-Dyn-Per-Token", "reason": null, "reconciledAt": "2026-09-21T17:59:08.869055+00:00", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-Dyn-Per-Token", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Mthreads_s4000", "taskId": "5005092", "taskType": "text-generation"}
|
||||
{"batchId": "72cb9a4a00eb4f81aa0d838e048a300f", "completedAt": "2026-09-21T17:59:07.220192+00:00", "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:54:45.272404+00:00", "framework": "vllm", "intentId": "5d0cb35457014256a231f3dff64bf6ad", "lastModified": "2026-09-12T12:30:14+00:00", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-MLX", "reason": null, "reconciledAt": "2026-09-21T17:59:08.868472+00:00", "repoId": "OpenBMB/MiniCPM5-2B-MLX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Iluvatar_bi-150", "taskId": "5005093", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.213781+00:00", "framework": "vllm_tokenizer_patch", "intentId": "db7b43e9ab3e44c78750def79629f872", "lastModified": "2026-08-24T15:14:56+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/SmolLM-135M-Instruct-quantized.w4a16", "repoId": "nm-testing/SmolLM-135M-Instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.213958+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4daa222bafcd45738690db6f36bcab64", "lastModified": "2026-08-24T16:38:03+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t", "repoId": "nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.214052+00:00", "framework": "vllm_tokenizer_patch", "intentId": "3c81ccfc8641416781f211e2db65fcee", "lastModified": "2026-08-24T15:42:55+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8-channel-a8-tensor", "repoId": "nm-testing/tinyllama-oneshot-w8-channel-a8-tensor", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.214141+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e41c11bd33754d7b8fd7cb4884703cc4", "lastModified": "2026-08-24T15:48:56+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2-asym", "repoId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2-asym", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.214230+00:00", "framework": "vllm_tokenizer_patch", "intentId": "0c57f9d9e63740daa308707843ecddf6", "lastModified": "2026-08-24T17:35:14+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-llama3-8b-Instruct-SmoothQuant-Fp8", "repoId": "nm-testing/Meta-llama3-8b-Instruct-SmoothQuant-Fp8", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.214317+00:00", "framework": "vllm_tokenizer_patch", "intentId": "654af64758bf449c98b09ebd5a2b4e08", "lastModified": "2026-08-24T17:33:00+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test-bos", "repoId": "nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test-bos", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.214405+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5b0f862fbe9a4012a55ac6ee6a72ecb6", "lastModified": "2026-08-24T17:58:05+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-one-shot-w4a16-group-packed", "repoId": "nm-testing/tinyllama-one-shot-w4a16-group-packed", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.214482+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c8f2268669d34a5c959d9107daf8839f", "lastModified": "2026-08-24T16:17:12+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8a8-channel-dynamic-token-v2", "repoId": "nm-testing/tinyllama-oneshot-w8a8-channel-dynamic-token-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.214557+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e17aa3e5748141ec8e6b4733ee31e48e", "lastModified": "2026-08-24T17:41:35+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test", "repoId": "nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.214632+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0a80c042fd8f4c8b81cbb504f6d789a2", "lastModified": "2026-08-24T14:45:05+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-W4-Group128-A16-Test", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W4-Group128-A16-Test", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.214795+00:00", "framework": "vllm_fix_tokenizer", "intentId": "cb85ea72e7b94f0c933cb6fe8eb3ebc2", "lastModified": "2026-08-24T16:10:08+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w4a16-channel-v2", "repoId": "nm-testing/tinyllama-oneshot-w4a16-channel-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.214874+00:00", "framework": "vllm_fix_tokenizer", "intentId": "3cdec3f9290344329987416daf1873f1", "lastModified": "2026-08-24T15:07:56+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Qwen2-1.5B-Instruct-FP8W8", "repoId": "nm-testing/Qwen2-1.5B-Instruct-FP8W8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.214950+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b3c7f12c69194cd1bba59204f214a6e6", "lastModified": "2026-08-24T19:10:38+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "repoId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.215024+00:00", "framework": "vllm_tokenizer_patch", "intentId": "2c20fe70e4474c86b48dfb902055185f", "lastModified": "2026-08-24T16:03:28+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/llama3-8b-w8_channel-a8_tensor-compressed", "repoId": "nm-testing/llama3-8b-w8_channel-a8_tensor-compressed", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.215092+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5e8ad38e922f4b13bee54b034074cb40", "lastModified": "2026-08-24T16:35:49+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-test", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-test", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.215159+00:00", "framework": "vllm_tokenizer_patch", "intentId": "0fe649cae6ce4904862627c2d651f645", "lastModified": "2026-08-24T16:01:21+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w4a16-group128-v2", "repoId": "nm-testing/tinyllama-oneshot-w4a16-group128-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.215225+00:00", "framework": "vllm_tokenizer_patch", "intentId": "caf9cba4f83c4dab9a9feba0803233b5", "lastModified": "2026-08-24T17:49:53+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-nonuniform-test", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-nonuniform-test", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.215290+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e2c8789d8ec6421d88ef2fd0b78c0524", "lastModified": "2026-08-24T16:40:22+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.215356+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6361e41718334851a26e5bb8122ab508", "lastModified": "2026-08-24T17:53:32+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-llama3-8b-Instruct-quant-FP8", "repoId": "nm-testing/Meta-llama3-8b-Instruct-quant-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.215421+00:00", "framework": "vllm-mlu", "intentId": "fde47dff96714c18813d2831df64e1b6", "lastModified": "2026-08-24T19:21:33+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-quantized.w8a8", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.215538+00:00", "framework": "vllm_tokenizer_patch", "intentId": "57f56887cb0c47cb99537a517f6aec0b", "lastModified": "2026-08-24T19:26:17+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-it-quantized.w4a16", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.215649+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e991be4b77304839bd9f41217411ae9d", "lastModified": "2026-08-24T17:02:50+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t-alt", "repoId": "nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t-alt", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.215741+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7f994eb0e2994cee8caa26988666664f", "lastModified": "2026-08-24T18:12:10+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.215827+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e858e50a015f4a98891b1f5af8ad7e66", "lastModified": "2026-08-24T18:26:59+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/nonuniform", "repoId": "nm-testing/nonuniform", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.215912+00:00", "framework": "vllm_tokenizer_patch", "intentId": "0ac1e3e15eb74638bea20f57a161efae", "lastModified": "2026-08-24T20:08:44+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.215998+00:00", "framework": "vllm_tokenizer_patch", "intentId": "352f2b816d654ba6961c19a38a80983b", "lastModified": "2026-08-24T19:59:13+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-FP8", "repoId": "RedHatAI/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.216084+00:00", "framework": "vllm_tokenizer_patch", "intentId": "27b170c7d68245248f38247c478544f3", "lastModified": "2026-08-24T19:36:07+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w4a16", "repoId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.216169+00:00", "framework": "vllm_tokenizer_patch", "intentId": "af1563f944d44564ba224320fcdd9269", "lastModified": "2026-09-11T15:37:46+00:00", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-base-32K", "repoId": "CohereLabs/tiny-aya-base-32K", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.216255+00:00", "framework": "vllm", "intentId": "7338af8e19e54e92acf847d4720f171c", "lastModified": "2026-08-24T20:22:22+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.216357+00:00", "framework": "vllm_fix_tokenizer", "intentId": "7495556f35b44d93bc0dbf69c1aa1360", "lastModified": "2026-08-24T20:04:01+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "repoId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.216432+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c72df26d9881474d807b800c370118da", "lastModified": "2026-08-24T19:34:25+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.216508+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0d3837a9fd704afbb56b5ac83beb1bb9", "lastModified": "2026-08-24T19:53:06+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "repoId": "neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.216584+00:00", "framework": "vllm_fix_tokenizer", "intentId": "272f1f4c4ac14242ba4c58416bef3100", "lastModified": "2026-08-24T19:39:27+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-FP8", "repoId": "neuralmagic/starcoder2-3b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.216659+00:00", "framework": "vllm_fix_tokenizer", "intentId": "833d042cd66941c39f777f0cbce002bb", "lastModified": "2026-08-24T20:22:00+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-it-quantized.w8a16", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.216742+00:00", "framework": "vllm_fix_tokenizer", "intentId": "59d3c7a567e840ab890c38e15ae7a375", "lastModified": "2026-08-24T20:22:06+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-quantized.w8a16", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.216817+00:00", "framework": "vllm_fix_tokenizer", "intentId": "257a85c3092745b4acb3513697133545", "lastModified": "2026-08-24T19:39:21+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-9b-it-quantized.w8a16", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.216890+00:00", "framework": "vllm_fix_tokenizer", "intentId": "404318b1ea8744fbbffea142d4255dbc", "lastModified": "2026-08-24T19:42:52+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-7b-FP8", "repoId": "neuralmagic/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.216965+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a685a0c1c5a3484d88a7ad4ff9dfa5d3", "lastModified": "2026-08-24T19:39:20+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-quantized.w8a16", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.217040+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ea115207309148c9b91e1f27aba8860f", "lastModified": "2026-08-24T18:09:20+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change", "repoId": "nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.217114+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0d3044b0193f4acd99dde045f9caa021", "lastModified": "2026-08-24T18:26:39+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8a8-static-v2", "repoId": "nm-testing/tinyllama-oneshot-w8a8-static-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.217190+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8818199809db4bd68492042608efaabd", "lastModified": "2026-08-24T18:28:40+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-marlin24-w4a16-group128", "repoId": "nm-testing/tinyllama-marlin24-w4a16-group128", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.217266+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d243f3bf72124680925200f48f1c6a23", "lastModified": "2026-08-24T18:24:11+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2", "repoId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.217341+00:00", "framework": "vllm_fix_tokenizer", "intentId": "04c169319da44707b0b65f2c696905aa", "lastModified": "2026-08-24T18:06:52+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3.1-8B-Instruct-FP8-hf", "repoId": "nm-testing/Meta-Llama-3.1-8B-Instruct-FP8-hf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.217416+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f51a3a79128a4b1abdc3ed1a095047a3", "lastModified": "2026-08-24T19:39:28+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-3b-quantized.w8a16", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.217491+00:00", "framework": "vllm_fix_tokenizer", "intentId": "750cded6318646e6988921e48664644e", "lastModified": "2026-08-24T19:51:52+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "repoId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.217566+00:00", "framework": "vllm_fix_tokenizer", "intentId": "20019d7d88c5487f8a705cdebcfc3321", "lastModified": "2026-08-24T20:01:57+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-it-quantized.w4a16", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.217642+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e75e8e12b57c47fe92b7b4882b9d4449", "lastModified": "2026-08-24T20:02:14+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-it-quantized.w8a16", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.217724+00:00", "framework": "vllm_fix_tokenizer", "intentId": "922f12ebb7a945ae9e8b65757ec84fee", "lastModified": "2026-08-24T20:26:53+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-9b-it-quantized.w8a16", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.217799+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1fc38ffcc03a4762a4885281b46e85be", "lastModified": "2026-08-26T12:23:38+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.217875+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f922d18700464577944a50b77bfad45e", "lastModified": "2026-09-03T18:32:29+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Apodex-1.1-mini-AWQ-INT4", "repoId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.217949+00:00", "framework": "vllm_fix_tokenizer", "intentId": "90ed1511bfa44aa19fee01dd8059f302", "lastModified": "2026-08-26T16:45:23+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "repoId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.218024+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f3f7547809924ba183855a98f299f1bd", "lastModified": "2026-09-09T06:27:24+00:00", "modelAddress": "https://modelscope.cn/models/ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "repoId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.218100+00:00", "framework": "vllm_fix_tokenizer", "intentId": "26ad390474c3453890d82b6980e3bd08", "lastModified": "2026-08-28T05:30:04+00:00", "modelAddress": "https://modelscope.cn/models/whcl412/mlx-LycheeAI-coder-1.7b", "repoId": "whcl412/mlx-LycheeAI-coder-1.7b", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.218175+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4138017fa814408c9fa55e57d6a3a0c9", "lastModified": "2026-08-26T19:32:38+00:00", "modelAddress": "https://modelscope.cn/models/pfnet/plamo-3-nict-8b-base", "repoId": "pfnet/plamo-3-nict-8b-base", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.218250+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4f716c76f9b44b77ba3a68ec037867f6", "lastModified": "2026-09-09T06:50:48+00:00", "modelAddress": "https://modelscope.cn/models/ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "repoId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.218324+00:00", "framework": "transformers", "intentId": "9fa149af1c2f456780b69d7555a46f66", "lastModified": "2026-08-24T22:55:11+00:00", "modelAddress": "https://modelscope.cn/models/BAAI/AquilaMed-RL", "repoId": "BAAI/AquilaMed-RL", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.218437+00:00", "framework": "transformers", "intentId": "456dd385497d4b14bc36f2d3288b3bbe", "lastModified": "2026-08-24T20:10:58+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.218549+00:00", "framework": "transformers", "intentId": "2d573356843f47688078eb0522fed710", "lastModified": "2026-08-24T19:54:53+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Llama-3.2-3B-Instruct-FP8", "repoId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.218660+00:00", "framework": "transformers", "intentId": "e31a762c77db4923b89859d34b2ba3e7", "lastModified": "2026-08-24T20:21:52+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-7b-quantized.w8a16", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "0335c7e4668aaa963303ebe91f80d6eb1e7e8d0299011bd85f7e05a4df031dc7", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.218778+00:00", "framework": "transformers", "intentId": "78e7038f452b4eda97009ee415a5fd1e", "lastModified": "2026-08-24T18:26:53+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8a16-per-channel", "repoId": "nm-testing/tinyllama-oneshot-w8a16-per-channel", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.218890+00:00", "framework": "transformers", "intentId": "178463e4292248a991872bf60db88e6c", "lastModified": "2026-09-10T07:52:22+00:00", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-4B", "repoId": "TokenRhythm/NeoHorse-1-4B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "72cb9a4a00eb4f81aa0d838e048a300f", "completedAt": "2026-09-21T17:59:07.220197+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:54:45.272511+00:00", "framework": "vllm", "intentId": "be47445997a84274a977bda0acc69d55", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
|
||||
{"batchId": "72cb9a4a00eb4f81aa0d838e048a300f", "completedAt": "2026-09-21T17:59:07.220195+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:54:45.272454+00:00", "framework": "vllm", "intentId": "874d32bd63454936b057f3f5a154fe5e", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
|
||||
{"batchId": "72cb9a4a00eb4f81aa0d838e048a300f", "completedAt": "2026-09-21T17:59:07.220184+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:54:45.272231+00:00", "framework": "vllm", "intentId": "875c0667c0994331a5616d5e3df41574", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Per-Token-Test", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"}
|
||||
|
||||
Reference in New Issue
Block a user