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

state: generation 8481 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-17 01:29:47 +00:00
parent 4b48e696b3
commit 72e2ebcbf1
10 changed files with 1965 additions and 1915 deletions
Download Patch File Download Diff File Expand all files Collapse all files

208
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-17T01:19:27.741411+00:00",
"lastSyncTime": "2026-09-17T01:19:27.449308+00:00",
"generatedAt": "2026-09-17T01:28:07.349913+00:00",
"lastSyncTime": "2026-09-17T01:28:07.114683+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1089,18 +1089,20 @@
"mthreads_s4000|vllm|text-generation|model_type:gemma4": {
"architectureSignature": "model_type:gemma4",
"architectures": [],
"evidenceCount": 2,
"expiresAt": "2026-10-15T07:13:14.095741+00:00",
"evidenceCount": 3,
"expiresAt": "2026-10-15T07:13:14.150584+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-15T07:13:14.095741+00:00",
"latestFailureAt": "2026-09-15T07:13:14.150584+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "gemma4",
"sourceModelIds": [
"mlx-community/gemma-4-e4b-it-OptiQ-4bit",
"mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit",
"mlx-community/gemma-4-31B-it-qat-OptiQ-4bit"
],
"sourceTaskIds": [
"4868223",
"4868225",
"4868229"
],
@@ -2372,10 +2374,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 55,
"ambiguous_runtime": 56,
"参数/模板问题": 2
},
"failureCount": 57,
"failureCount": 58,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -2385,8 +2387,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 57,
"unresolvedFailureCount": 57
"total": 58,
"unresolvedFailureCount": 58
},
"MetaX_c-500|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -2502,14 +2504,14 @@
"unresolvedFailureCount": 1
},
"Mthreads_s4000|vllm|text-generation": {
"attributableFailureCount": 45,
"decisionFailureRate": 0.8824,
"decisionSuccessRate": 0.1176,
"decisionTotal": 51,
"attributableFailureCount": 46,
"decisionFailureRate": 0.8846,
"decisionSuccessRate": 0.1154,
"decisionTotal": 52,
"failureBreakdown": {
"ambiguous_runtime": 43,
"backend_operator": 4,
"framework_architecture_unsupported": 34,
"framework_architecture_unsupported": 35,
"memory_capacity": 1,
"model_load": 2,
"repository_structure": 1,
@@ -2517,17 +2519,17 @@
"tokenizer_compatibility": 1,
"参数/模板问题": 3
},
"failureCount": 91,
"failureRate": 0.9381,
"failureCount": 92,
"failureRate": 0.9388,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 6,
"successRate": 0.0619,
"successRate": 0.0612,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 97,
"total": 98,
"unresolvedFailureCount": 46
},
"Sunrise_pt-200-x1|unknown|text-generation": {
@@ -2833,14 +2835,14 @@
"unresolvedFailureCount": 904
},
"vllm": {
"attributableFailureCount": 384,
"decisionFailureRate": 0.96,
"decisionSuccessRate": 0.04,
"decisionTotal": 400,
"attributableFailureCount": 385,
"decisionFailureRate": 0.9601,
"decisionSuccessRate": 0.0399,
"decisionTotal": 401,
"failureBreakdown": {
"ambiguous_runtime": 225,
"backend_operator": 36,
"framework_architecture_unsupported": 287,
"framework_architecture_unsupported": 288,
"memory_capacity": 7,
"model_load": 31,
"platform_infrastructure": 2,
@@ -2849,14 +2851,14 @@
"tokenizer_compatibility": 9,
"参数/模板问题": 31
},
"failureCount": 642,
"failureCount": 643,
"failureRate": 0.9757,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 16,
"successRate": 0.0243,
"total": 658,
"total": 659,
"unresolvedFailureCount": 256
},
"vllm-mlu": {
@@ -2930,7 +2932,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 57,
"failureBreakdown": {
"ambiguous_runtime": 60,
"ambiguous_runtime": 61,
"backend_operator": 2,
"framework_architecture_unsupported": 9,
"model_load": 1,
@@ -2938,15 +2940,15 @@
"tokenizer_compatibility": 45,
"参数/模板问题": 8
},
"failureCount": 132,
"failureCount": 133,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 7,
"successCount": 0,
"successRate": 0.0,
"total": 132,
"unresolvedFailureCount": 68
"total": 133,
"unresolvedFailureCount": 69
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 6,
@@ -2968,7 +2970,7 @@
"unresolvedFailureCount": 6
}
},
"generatedAt": "2026-09-17T01:19:27.735415+00:00",
"generatedAt": "2026-09-17T01:28:07.344195+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 51,
@@ -3165,20 +3167,20 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 100,
"ambiguous_runtime": 101,
"memory_capacity": 1,
"参数/模板问题": 2,
"验证失败": 23
},
"failureCount": 126,
"failureCount": 127,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 126,
"unresolvedFailureCount": 125
"total": 127,
"unresolvedFailureCount": 126
},
"MetaX_c-500": {
"attributableFailureCount": 59,
@@ -3206,14 +3208,14 @@
"unresolvedFailureCount": 78
},
"Mthreads_s4000": {
"attributableFailureCount": 46,
"decisionFailureRate": 0.8519,
"decisionSuccessRate": 0.1481,
"decisionTotal": 54,
"attributableFailureCount": 47,
"decisionFailureRate": 0.8545,
"decisionSuccessRate": 0.1455,
"decisionTotal": 55,
"failureBreakdown": {
"ambiguous_runtime": 43,
"backend_operator": 4,
"framework_architecture_unsupported": 34,
"framework_architecture_unsupported": 35,
"memory_capacity": 1,
"model_load": 3,
"repository_structure": 1,
@@ -3222,14 +3224,14 @@
"参数/模板问题": 11,
"验证失败": 26
},
"failureCount": 126,
"failureRate": 0.9403,
"failureCount": 127,
"failureRate": 0.9407,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 8,
"successRate": 0.0597,
"total": 134,
"successRate": 0.0593,
"total": 135,
"unresolvedFailureCount": 80
},
"Sunrise_pt-200-x1": {
@@ -5098,10 +5100,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 5,
"ambiguous_runtime": 6,
"参数/模板问题": 1
},
"failureCount": 6,
"failureCount": 7,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "qwen3_5",
@@ -5113,8 +5115,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 6,
"unresolvedFailureCount": 6
"total": 7,
"unresolvedFailureCount": 7
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3|none": {
"attributableFailureCount": 0,
@@ -5642,14 +5644,14 @@
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|gemma4|none": {
"attributableFailureCount": 2,
"attributableFailureCount": 3,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"decisionTotal": 3,
"failureBreakdown": {
"framework_architecture_unsupported": 2
"framework_architecture_unsupported": 3
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "gemma4",
@@ -5661,7 +5663,7 @@
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 2,
"total": 3,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|glm_ocr|fp8": {
@@ -6802,18 +6804,18 @@
"unresolvedFailureCount": 1
},
"Mthreads_s4000|vllm|text-generation": {
"attributableFailureCount": 11,
"consecutiveFailures": 11,
"attributableFailureCount": 12,
"consecutiveFailures": 12,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 11,
"decisionTotal": 12,
"failureBreakdown": {
"ambiguous_runtime": 6,
"framework_architecture_unsupported": 10,
"framework_architecture_unsupported": 11,
"tokenizer_compatibility": 1
},
"failureCount": 17,
"failureCount": 18,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -6825,7 +6827,7 @@
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 17,
"total": 18,
"unresolvedFailureCount": 6
},
"Sunrise_pt-200-x1|unknown|text-generation": {
@@ -7091,18 +7093,18 @@
"unresolvedFailureCount": 2
},
"Mthreads_s4000|vllm|text-generation|gemma4|none": {
"attributableFailureCount": 2,
"consecutiveFailures": 2,
"attributableFailureCount": 3,
"consecutiveFailures": 3,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"decisionTotal": 3,
"failureBreakdown": {
"framework_architecture_unsupported": 2
"framework_architecture_unsupported": 3
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm",
"lastTerminalAt": "2026-09-17T01:19:27.449308+00:00",
"lastTerminalAt": "2026-09-17T01:28:07.114653+00:00",
"modelType": "gemma4",
"pendingCount": 0,
"pendingRate": 0.0,
@@ -7112,7 +7114,7 @@
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 2,
"total": 3,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|mistral3|none": {
@@ -9730,6 +9732,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5|none|12": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 12,
"modelType": "qwen3_5",
"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|none|33": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -10733,6 +10759,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|gemma4|none|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 32,
"modelType": "gemma4",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|gemma4|none|34": {
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
@@ -11617,17 +11667,17 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 2072,
"totalRecords": 2175,
"terminalRecords": 2074,
"totalRecords": 2177,
"totals": {
"attributableFailureCount": 674,
"decisionFailureRate": 0.888,
"decisionSuccessRate": 0.112,
"decisionTotal": 759,
"attributableFailureCount": 675,
"decisionFailureRate": 0.8882,
"decisionSuccessRate": 0.1118,
"decisionTotal": 760,
"failureBreakdown": {
"ambiguous_runtime": 506,
"ambiguous_runtime": 507,
"backend_operator": 46,
"framework_architecture_unsupported": 445,
"framework_architecture_unsupported": 446,
"memory_capacity": 12,
"model_load": 85,
"platform_infrastructure": 10,
@@ -11637,29 +11687,29 @@
"参数/模板问题": 124,
"验证失败": 673
},
"failureCount": 1987,
"failureCount": 1989,
"failureRate": 0.959,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 10,
"successCount": 85,
"successRate": 0.041,
"total": 2072,
"unresolvedFailureCount": 1303
"total": 2074,
"unresolvedFailureCount": 1304
},
"warnings": [
"GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU 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 Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
"组合 Biren_166m|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Biren_166m|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Vastai_va16|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。",
@@ -11684,6 +11734,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 2175,
"summarizedRecords": 2177,
"version": 1
}