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

state: generation 8478 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-17 01:21:19 +00:00
parent 5264c17a73
commit cd2c85c32c
10 changed files with 2056 additions and 2026 deletions
Download Patch File Download Diff File Expand all files Collapse all files

236
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-17T01:10:41.663647+00:00",
"lastSyncTime": "2026-09-17T01:10:41.230667+00:00",
"generatedAt": "2026-09-17T01:19:27.741411+00:00",
"lastSyncTime": "2026-09-17T01:19:27.449308+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1089,17 +1089,19 @@
"mthreads_s4000|vllm|text-generation|model_type:gemma4": {
"architectureSignature": "model_type:gemma4",
"architectures": [],
"evidenceCount": 1,
"expiresAt": "2026-10-15T07:13:14.091353+00:00",
"evidenceCount": 2,
"expiresAt": "2026-10-15T07:13:14.095741+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-15T07:13:14.091353+00:00",
"latestFailureAt": "2026-09-15T07:13:14.095741+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "gemma4",
"sourceModelIds": [
"mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit",
"mlx-community/gemma-4-31B-it-qat-OptiQ-4bit"
],
"sourceTaskIds": [
"4868225",
"4868229"
],
"targetGpu": "Mthreads_s4000",
@@ -1173,17 +1175,19 @@
"mthreads_s4000|vllm|text-generation|model_type:qwen3_5_moe": {
"architectureSignature": "model_type:qwen3_5_moe",
"architectures": [],
"evidenceCount": 1,
"expiresAt": "2026-10-15T07:13:14.086293+00:00",
"evidenceCount": 2,
"expiresAt": "2026-10-15T07:13:14.093936+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-15T07:13:14.086293+00:00",
"latestFailureAt": "2026-09-15T07:13:14.093936+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "qwen3_5_moe",
"sourceModelIds": [
"mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit",
"mlx-community/XYZ-Aquila-mini-OptiQ-4bit"
],
"sourceTaskIds": [
"4868226",
"4868227"
],
"targetGpu": "Mthreads_s4000",
@@ -2498,14 +2502,14 @@
"unresolvedFailureCount": 1
},
"Mthreads_s4000|vllm|text-generation": {
"attributableFailureCount": 43,
"decisionFailureRate": 0.8776,
"decisionSuccessRate": 0.1224,
"decisionTotal": 49,
"attributableFailureCount": 45,
"decisionFailureRate": 0.8824,
"decisionSuccessRate": 0.1176,
"decisionTotal": 51,
"failureBreakdown": {
"ambiguous_runtime": 43,
"backend_operator": 4,
"framework_architecture_unsupported": 32,
"framework_architecture_unsupported": 34,
"memory_capacity": 1,
"model_load": 2,
"repository_structure": 1,
@@ -2513,17 +2517,17 @@
"tokenizer_compatibility": 1,
"参数/模板问题": 3
},
"failureCount": 89,
"failureRate": 0.9368,
"failureCount": 91,
"failureRate": 0.9381,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 6,
"successRate": 0.0632,
"successRate": 0.0619,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 95,
"total": 97,
"unresolvedFailureCount": 46
},
"Sunrise_pt-200-x1|unknown|text-generation": {
@@ -2742,14 +2746,14 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 55,
"failureBreakdown": {
"ambiguous_runtime": 23,
"ambiguous_runtime": 24,
"framework_architecture_unsupported": 43,
"memory_capacity": 1,
"model_load": 5,
"repository_structure": 4,
"runtime_memory": 2
},
"failureCount": 78,
"failureCount": 79,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2759,8 +2763,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 78,
"unresolvedFailureCount": 23
"total": 79,
"unresolvedFailureCount": 24
}
},
"frameworkSummaries": {
@@ -2829,14 +2833,14 @@
"unresolvedFailureCount": 904
},
"vllm": {
"attributableFailureCount": 382,
"decisionFailureRate": 0.9598,
"decisionSuccessRate": 0.0402,
"decisionTotal": 398,
"attributableFailureCount": 384,
"decisionFailureRate": 0.96,
"decisionSuccessRate": 0.04,
"decisionTotal": 400,
"failureBreakdown": {
"ambiguous_runtime": 224,
"ambiguous_runtime": 225,
"backend_operator": 36,
"framework_architecture_unsupported": 285,
"framework_architecture_unsupported": 287,
"memory_capacity": 7,
"model_load": 31,
"platform_infrastructure": 2,
@@ -2845,15 +2849,15 @@
"tokenizer_compatibility": 9,
"参数/模板问题": 31
},
"failureCount": 639,
"failureRate": 0.9756,
"failureCount": 642,
"failureRate": 0.9757,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 16,
"successRate": 0.0244,
"total": 655,
"unresolvedFailureCount": 255
"successRate": 0.0243,
"total": 658,
"unresolvedFailureCount": 256
},
"vllm-mlu": {
"attributableFailureCount": 9,
@@ -2964,7 +2968,7 @@
"unresolvedFailureCount": 6
}
},
"generatedAt": "2026-09-17T01:10:41.658007+00:00",
"generatedAt": "2026-09-17T01:19:27.735415+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 51,
@@ -3202,14 +3206,14 @@
"unresolvedFailureCount": 78
},
"Mthreads_s4000": {
"attributableFailureCount": 44,
"decisionFailureRate": 0.8462,
"decisionSuccessRate": 0.1538,
"decisionTotal": 52,
"attributableFailureCount": 46,
"decisionFailureRate": 0.8519,
"decisionSuccessRate": 0.1481,
"decisionTotal": 54,
"failureBreakdown": {
"ambiguous_runtime": 43,
"backend_operator": 4,
"framework_architecture_unsupported": 32,
"framework_architecture_unsupported": 34,
"memory_capacity": 1,
"model_load": 3,
"repository_structure": 1,
@@ -3218,14 +3222,14 @@
"参数/模板问题": 11,
"验证失败": 26
},
"failureCount": 124,
"failureRate": 0.9394,
"failureCount": 126,
"failureRate": 0.9403,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 8,
"successRate": 0.0606,
"total": 132,
"successRate": 0.0597,
"total": 134,
"unresolvedFailureCount": 80
},
"Sunrise_pt-200-x1": {
@@ -3282,7 +3286,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 62,
"failureBreakdown": {
"ambiguous_runtime": 28,
"ambiguous_runtime": 29,
"framework_architecture_unsupported": 49,
"memory_capacity": 1,
"model_load": 5,
@@ -3291,15 +3295,15 @@
"参数/模板问题": 10,
"验证失败": 27
},
"failureCount": 127,
"failureCount": 128,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 127,
"unresolvedFailureCount": 65
"total": 128,
"unresolvedFailureCount": 66
}
},
"observedGpuMemoryGiB": {
@@ -5638,14 +5642,14 @@
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|gemma4|none": {
"attributableFailureCount": 1,
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 1
"framework_architecture_unsupported": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "gemma4",
@@ -5657,7 +5661,7 @@
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|glm_ocr|fp8": {
@@ -5820,14 +5824,14 @@
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|qwen3_5_moe|none": {
"attributableFailureCount": 1,
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 1
"framework_architecture_unsupported": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "qwen3_5_moe",
@@ -5839,7 +5843,7 @@
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|qwen3|none": {
@@ -6798,18 +6802,18 @@
"unresolvedFailureCount": 1
},
"Mthreads_s4000|vllm|text-generation": {
"attributableFailureCount": 9,
"consecutiveFailures": 9,
"attributableFailureCount": 11,
"consecutiveFailures": 11,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 9,
"decisionTotal": 11,
"failureBreakdown": {
"ambiguous_runtime": 6,
"framework_architecture_unsupported": 8,
"framework_architecture_unsupported": 10,
"tokenizer_compatibility": 1
},
"failureCount": 15,
"failureCount": 17,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -6821,7 +6825,7 @@
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 15,
"total": 17,
"unresolvedFailureCount": 6
},
"Sunrise_pt-200-x1|unknown|text-generation": {
@@ -6983,22 +6987,22 @@
"unresolvedFailureCount": 2
},
"hygon_k100-ai|vllm|text-generation": {
"attributableFailureCount": 14,
"consecutiveFailures": 14,
"attributableFailureCount": 13,
"consecutiveFailures": 13,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 14,
"decisionTotal": 13,
"failureBreakdown": {
"ambiguous_runtime": 6,
"framework_architecture_unsupported": 13,
"ambiguous_runtime": 7,
"framework_architecture_unsupported": 12,
"model_load": 1
},
"failureCount": 20,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-17T01:10:41.230651+00:00",
"lastTerminalAt": "2026-09-17T01:19:27.449287+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -7007,7 +7011,7 @@
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 6
"unresolvedFailureCount": 7
}
},
"recentProfileCombinationStats": {
@@ -7087,18 +7091,18 @@
"unresolvedFailureCount": 2
},
"Mthreads_s4000|vllm|text-generation|gemma4|none": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"attributableFailureCount": 2,
"consecutiveFailures": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 1
"framework_architecture_unsupported": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"lastTerminalAt": "2026-09-17T01:10:41.230600+00:00",
"lastTerminalAt": "2026-09-17T01:19:27.449308+00:00",
"modelType": "gemma4",
"pendingCount": 0,
"pendingRate": 0.0,
@@ -7108,7 +7112,7 @@
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|mistral3|none": {
@@ -7137,18 +7141,18 @@
"unresolvedFailureCount": 1
},
"Mthreads_s4000|vllm|text-generation|qwen3_5_moe|none": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"attributableFailureCount": 2,
"consecutiveFailures": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 1
"framework_architecture_unsupported": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"lastTerminalAt": "2026-09-16T20:22:19.008738+00:00",
"lastTerminalAt": "2026-09-17T01:19:27.449250+00:00",
"modelType": "qwen3_5_moe",
"pendingCount": 0,
"pendingRate": 0.0,
@@ -7158,7 +7162,7 @@
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
}
},
@@ -10730,14 +10734,14 @@
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|gemma4|none|34": {
"attributableFailureCount": 1,
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 1
"framework_architecture_unsupported": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 34,
@@ -10750,7 +10754,7 @@
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|glm_ocr|fp8|30": {
@@ -10941,6 +10945,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|qwen3_5_moe|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": "qwen3_5_moe",
"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|qwen3_5_moe|none|35": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -11589,17 +11617,17 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 2069,
"totalRecords": 2172,
"terminalRecords": 2072,
"totalRecords": 2175,
"totals": {
"attributableFailureCount": 672,
"decisionFailureRate": 0.8877,
"decisionSuccessRate": 0.1123,
"decisionTotal": 757,
"attributableFailureCount": 674,
"decisionFailureRate": 0.888,
"decisionSuccessRate": 0.112,
"decisionTotal": 759,
"failureBreakdown": {
"ambiguous_runtime": 505,
"ambiguous_runtime": 506,
"backend_operator": 46,
"framework_architecture_unsupported": 443,
"framework_architecture_unsupported": 445,
"memory_capacity": 12,
"model_load": 85,
"platform_infrastructure": 10,
@@ -11609,28 +11637,28 @@
"参数/模板问题": 124,
"验证失败": 673
},
"failureCount": 1984,
"failureRate": 0.9589,
"failureCount": 1987,
"failureRate": 0.959,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 10,
"successCount": 85,
"successRate": 0.0411,
"total": 2069,
"unresolvedFailureCount": 1302
"successRate": 0.041,
"total": 2072,
"unresolvedFailureCount": 1303
},
"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 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 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。",
@@ -11656,6 +11684,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 2172,
"summarizedRecords": 2175,
"version": 1
}