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

state: generation 19463 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-10-02 02:26:28 +00:00
parent 2ef8a50bef
commit b7fcfef550
8 changed files with 1506 additions and 1413 deletions
Download Patch File Download Diff File Expand all files Collapse all files

232
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-10-02T02:11:15.894943+00:00",
"lastSyncTime": "2026-10-02T02:11:15.645478+00:00",
"generatedAt": "2026-10-02T02:23:34.025020+00:00",
"lastSyncTime": "2026-10-02T02:23:33.763206+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -4989,10 +4989,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 152,
"ambiguous_runtime": 153,
"参数/模板问题": 3
},
"failureCount": 155,
"failureCount": 156,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -5002,8 +5002,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 155,
"unresolvedFailureCount": 155
"total": 156,
"unresolvedFailureCount": 156
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 61,
@@ -5467,18 +5467,18 @@
"unresolvedFailureCount": 296
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 119,
"attributableFailureCount": 120,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 119,
"decisionTotal": 120,
"failureBreakdown": {
"backend_operator": 9,
"framework_architecture_unsupported": 18,
"framework_architecture_unsupported": 19,
"platform_infrastructure": 22,
"tokenizer_compatibility": 92,
"参数/模板问题": 6
},
"failureCount": 147,
"failureCount": 148,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -5488,20 +5488,20 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 147,
"total": 148,
"unresolvedFailureCount": 6
},
"Sunrise_pt-200-x1|vllm|text-generation": {
"attributableFailureCount": 617,
"attributableFailureCount": 618,
"decisionFailureRate": 0.9968,
"decisionSuccessRate": 0.0032,
"decisionTotal": 619,
"decisionTotal": 620,
"failureBreakdown": {
"ambiguous_runtime": 109,
"architecture_compatibility": 43,
"backend_operator": 28,
"context_length": 34,
"framework_architecture_unsupported": 143,
"framework_architecture_unsupported": 144,
"memory_capacity": 113,
"platform_infrastructure": 211,
"repository_structure": 75,
@@ -5509,7 +5509,7 @@
"tokenizer_compatibility": 180,
"参数/模板问题": 9
},
"failureCount": 946,
"failureCount": 947,
"failureRate": 0.9979,
"framework": "vllm",
"pendingCount": 0,
@@ -5519,7 +5519,7 @@
"successRate": 0.0021,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 948,
"total": 949,
"unresolvedFailureCount": 118
},
"Sunrise_pt-200-x1|vllm|unknown": {
@@ -6021,17 +6021,17 @@
"unresolvedFailureCount": 6473
},
"vllm": {
"attributableFailureCount": 3638,
"attributableFailureCount": 3639,
"decisionFailureRate": 0.9727,
"decisionSuccessRate": 0.0273,
"decisionTotal": 3740,
"decisionTotal": 3741,
"failureBreakdown": {
"ambiguous_runtime": 1594,
"architecture_compatibility": 112,
"attention_backend": 3,
"backend_operator": 93,
"context_length": 161,
"framework_architecture_unsupported": 1367,
"framework_architecture_unsupported": 1368,
"memory_capacity": 725,
"model_load": 221,
"platform_infrastructure": 875,
@@ -6040,14 +6040,14 @@
"tokenizer_compatibility": 420,
"参数/模板问题": 50
},
"failureCount": 6157,
"failureCount": 6158,
"failureRate": 0.9837,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 875,
"successCount": 102,
"successRate": 0.0163,
"total": 6259,
"total": 6260,
"unresolvedFailureCount": 1644
},
"vllm-customized": {
@@ -6145,29 +6145,29 @@
"unresolvedFailureCount": 31
},
"vllm_fix_tokenizer": {
"attributableFailureCount": 159,
"decisionFailureRate": 0.9695,
"decisionSuccessRate": 0.0305,
"decisionTotal": 164,
"attributableFailureCount": 160,
"decisionFailureRate": 0.9697,
"decisionSuccessRate": 0.0303,
"decisionTotal": 165,
"failureBreakdown": {
"ambiguous_runtime": 343,
"ambiguous_runtime": 344,
"backend_operator": 9,
"framework_architecture_unsupported": 39,
"framework_architecture_unsupported": 40,
"memory_capacity": 10,
"model_load": 9,
"platform_infrastructure": 22,
"tokenizer_compatibility": 92,
"参数/模板问题": 13
},
"failureCount": 537,
"failureCount": 539,
"failureRate": 0.9908,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 22,
"successCount": 5,
"successRate": 0.0092,
"total": 542,
"unresolvedFailureCount": 356
"total": 544,
"unresolvedFailureCount": 357
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 143,
@@ -6198,7 +6198,7 @@
"unresolvedFailureCount": 227
}
},
"generatedAt": "2026-10-02T02:11:15.881373+00:00",
"generatedAt": "2026-10-02T02:23:34.011283+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 114,
@@ -6430,7 +6430,7 @@
"decisionSuccessRate": 0.066,
"decisionTotal": 106,
"failureBreakdown": {
"ambiguous_runtime": 240,
"ambiguous_runtime": 241,
"backend_operator": 23,
"framework_architecture_unsupported": 37,
"memory_capacity": 3,
@@ -6443,15 +6443,15 @@
"日志缺失": 1,
"验证失败": 23
},
"failureCount": 410,
"failureRate": 0.9832,
"failureCount": 411,
"failureRate": 0.9833,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 7,
"successRate": 0.0168,
"total": 417,
"unresolvedFailureCount": 310
"successRate": 0.0167,
"total": 418,
"unresolvedFailureCount": 311
},
"Kunlunxin_r-200-8f": {
"attributableFailureCount": 0,
@@ -6534,16 +6534,16 @@
"unresolvedFailureCount": 301
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 755,
"decisionFailureRate": 0.8882,
"decisionSuccessRate": 0.1118,
"decisionTotal": 850,
"attributableFailureCount": 757,
"decisionFailureRate": 0.8885,
"decisionSuccessRate": 0.1115,
"decisionTotal": 852,
"failureBreakdown": {
"ambiguous_runtime": 162,
"architecture_compatibility": 44,
"backend_operator": 37,
"context_length": 39,
"framework_architecture_unsupported": 163,
"framework_architecture_unsupported": 165,
"memory_capacity": 113,
"platform_infrastructure": 233,
"repository_structure": 83,
@@ -6552,14 +6552,14 @@
"参数/模板问题": 228,
"验证失败": 32
},
"failureCount": 1410,
"failureRate": 0.9369,
"failureCount": 1412,
"failureRate": 0.937,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 233,
"successCount": 95,
"successRate": 0.0631,
"total": 1505,
"successRate": 0.063,
"total": 1507,
"unresolvedFailureCount": 422
},
"Vastai_va16": {
@@ -18307,6 +18307,29 @@
"total": 3,
"unresolvedFailureCount": 3
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_moe_text|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "qwen3_5_moe_text",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_moe|compressed-tensors": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -21642,6 +21665,29 @@
"total": 5,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|param2moe|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "param2moe",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_moe|compressed-tensors": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -21875,14 +21921,15 @@
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|compressed-tensors": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1,
"platform_infrastructure": 2
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "qwen3_5",
@@ -21894,7 +21941,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 2,
"total": 3,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|gptq": {
@@ -45789,6 +45836,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_moe_text|none|35": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 35,
"modelType": "qwen3_5_moe_text",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_moe|compressed-tensors|34": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -51113,6 +51184,30 @@
"total": 2,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|param2moe|none|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 34,
"modelType": "param2moe",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_moe|compressed-tensors|34": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -51499,14 +51594,15 @@
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|compressed-tensors|33": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1,
"platform_infrastructure": 1
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 33,
@@ -51519,7 +51615,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|compressed-tensors|34": {
@@ -54622,20 +54718,20 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17218,
"totalRecords": 17439,
"terminalRecords": 17221,
"totalRecords": 17442,
"totals": {
"attributableFailureCount": 6172,
"attributableFailureCount": 6174,
"decisionFailureRate": 0.8636,
"decisionSuccessRate": 0.1364,
"decisionTotal": 7147,
"decisionTotal": 7149,
"failureBreakdown": {
"ambiguous_runtime": 4503,
"ambiguous_runtime": 4504,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 128,
"context_length": 327,
"framework_architecture_unsupported": 2214,
"framework_architecture_unsupported": 2216,
"memory_capacity": 1206,
"model_load": 553,
"platform_infrastructure": 945,
@@ -54646,30 +54742,30 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16243,
"failureCount": 16246,
"failureRate": 0.9434,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 945,
"successCount": 975,
"successRate": 0.0566,
"total": 17218,
"unresolvedFailureCount": 9126
"total": 17221,
"unresolvedFailureCount": 9127
},
"warnings": [
"GPU Iluvatar_mrv-100 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 Biren_166m 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 Cambricon_mlu-370-x4 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 hygon_k100-ai 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 Mthreads_s4000 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 Vastai_va16 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 Iluvatar_bi-150 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。",
"GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
"组合 Ascend_910-b4|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Kunlunxin_p-800|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -54714,6 +54810,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17439,
"summarizedRecords": 17442,
"version": 1
}