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

state: generation 10032 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-19 23:06:17 +00:00
parent 4434794662
commit cf9d447a93
10 changed files with 1763 additions and 1766 deletions
Download Patch File Download Diff File Expand all files Collapse all files

148
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-19T22:42:49.622484+00:00",
"lastSyncTime": "2026-09-19T22:42:49.322287+00:00",
"generatedAt": "2026-09-19T23:04:04.019390+00:00",
"lastSyncTime": "2026-09-19T23:04:02.598874+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1663,26 +1663,26 @@
"vastai_va16|vllm|text-generation|model_type:qwen3_5": {
"architectureSignature": "model_type:qwen3_5",
"architectures": [],
"evidenceCount": 9,
"expiresAt": "2026-10-19T02:03:21+00:00",
"evidenceCount": 10,
"expiresAt": "2026-10-19T23:03:21+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-19T02:03:21+00:00",
"latestFailureAt": "2026-09-19T23:03:21+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "qwen3_5",
"sourceModelIds": [
"Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B",
"r0b0tlab/Qwen3.8-27B-NVFP4-MTP-sm121",
"ornith-ai/Ornith-1.5-9B-MLX-8bit",
"cyankiwi/Ornith-1.5-9B-AWQ-INT4",
"callmezcc/Qwen3.8-27B-GPTQ-W4A16",
"cyankiwi/Ornith-1.5-9B-AWQ-FP8"
"callmezcc/Qwen3.8-27B-GPTQ-W4A16"
],
"sourceTaskIds": [
"4609086",
"4609094",
"4609081",
"4609101",
"4609083",
"4609077"
"4609083"
],
"targetGpu": "Vastai_va16",
"taskType": "text-generation"
@@ -2052,21 +2052,21 @@
"decisionSuccessRate": 0.5385,
"decisionTotal": 13,
"failureBreakdown": {
"ambiguous_runtime": 10,
"ambiguous_runtime": 11,
"framework_architecture_unsupported": 6
},
"failureCount": 16,
"failureRate": 0.6957,
"failureCount": 17,
"failureRate": 0.7083,
"framework": "vllm-mlu",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 7,
"successRate": 0.3043,
"successRate": 0.2917,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 23,
"unresolvedFailureCount": 10
"total": 24,
"unresolvedFailureCount": 11
},
"Cambricon_mlu-370-x8|unknown|text-generation": {
"attributableFailureCount": 8,
@@ -2678,17 +2678,17 @@
"unresolvedFailureCount": 9
},
"Vastai_va16|vllm|text-generation": {
"attributableFailureCount": 61,
"attributableFailureCount": 62,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 61,
"decisionTotal": 62,
"failureBreakdown": {
"ambiguous_runtime": 76,
"framework_architecture_unsupported": 55,
"framework_architecture_unsupported": 56,
"memory_capacity": 1,
"model_load": 5
},
"failureCount": 137,
"failureCount": 138,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2698,7 +2698,7 @@
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 137,
"total": 138,
"unresolvedFailureCount": 76
},
"hygon_k100-ai|llamacpp|text-generation": {
@@ -2862,14 +2862,14 @@
"unresolvedFailureCount": 910
},
"vllm": {
"attributableFailureCount": 428,
"decisionFailureRate": 0.8612,
"decisionSuccessRate": 0.1388,
"decisionTotal": 497,
"attributableFailureCount": 429,
"decisionFailureRate": 0.8614,
"decisionSuccessRate": 0.1386,
"decisionTotal": 498,
"failureBreakdown": {
"ambiguous_runtime": 247,
"backend_operator": 40,
"framework_architecture_unsupported": 322,
"framework_architecture_unsupported": 323,
"memory_capacity": 7,
"model_load": 33,
"platform_infrastructure": 2,
@@ -2878,14 +2878,14 @@
"tokenizer_compatibility": 12,
"参数/模板问题": 40
},
"failureCount": 717,
"failureRate": 0.9122,
"failureCount": 718,
"failureRate": 0.9123,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 69,
"successRate": 0.0878,
"total": 786,
"successRate": 0.0877,
"total": 787,
"unresolvedFailureCount": 287
},
"vllm-mlu": {
@@ -2894,20 +2894,20 @@
"decisionSuccessRate": 0.5,
"decisionTotal": 36,
"failureBreakdown": {
"ambiguous_runtime": 41,
"ambiguous_runtime": 42,
"framework_architecture_unsupported": 17,
"tokenizer_compatibility": 1,
"参数/模板问题": 3
},
"failureCount": 62,
"failureRate": 0.775,
"failureCount": 63,
"failureRate": 0.7778,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 18,
"successRate": 0.225,
"total": 80,
"unresolvedFailureCount": 44
"successRate": 0.2222,
"total": 81,
"unresolvedFailureCount": 45
},
"vllm-patch-tokenizer": {
"attributableFailureCount": 17,
@@ -2998,7 +2998,7 @@
"unresolvedFailureCount": 22
}
},
"generatedAt": "2026-09-19T22:42:49.617126+00:00",
"generatedAt": "2026-09-19T23:04:04.013701+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 62,
@@ -3080,22 +3080,22 @@
"decisionSuccessRate": 0.234,
"decisionTotal": 47,
"failureBreakdown": {
"ambiguous_runtime": 49,
"ambiguous_runtime": 50,
"framework_architecture_unsupported": 33,
"memory_capacity": 1,
"tokenizer_compatibility": 2,
"参数/模板问题": 1,
"验证失败": 39
},
"failureCount": 125,
"failureRate": 0.9191,
"failureCount": 126,
"failureRate": 0.9197,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 11,
"successRate": 0.0809,
"total": 136,
"unresolvedFailureCount": 89
"successRate": 0.0803,
"total": 137,
"unresolvedFailureCount": 90
},
"Cambricon_mlu-370-x8": {
"attributableFailureCount": 23,
@@ -3288,26 +3288,26 @@
"unresolvedFailureCount": 51
},
"Vastai_va16": {
"attributableFailureCount": 67,
"decisionFailureRate": 0.7791,
"decisionSuccessRate": 0.2209,
"decisionTotal": 86,
"attributableFailureCount": 68,
"decisionFailureRate": 0.7816,
"decisionSuccessRate": 0.2184,
"decisionTotal": 87,
"failureBreakdown": {
"ambiguous_runtime": 85,
"framework_architecture_unsupported": 60,
"framework_architecture_unsupported": 61,
"memory_capacity": 1,
"model_load": 6,
"参数/模板问题": 15,
"验证失败": 130
},
"failureCount": 297,
"failureRate": 0.9399,
"failureCount": 298,
"failureRate": 0.9401,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 19,
"successRate": 0.0601,
"total": 316,
"successRate": 0.0599,
"total": 317,
"unresolvedFailureCount": 230
},
"hygon_k100-ai": {
@@ -4388,9 +4388,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 3
"ambiguous_runtime": 4
},
"failureCount": 3,
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm-mlu",
"modelType": "llama",
@@ -4402,8 +4402,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 3,
"unresolvedFailureCount": 3
"total": 4,
"unresolvedFailureCount": 4
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|muse_glimmer|none": {
"attributableFailureCount": 1,
@@ -8657,7 +8657,7 @@
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-19T02:10:43.202143+00:00",
"lastTerminalAt": "2026-09-19T23:04:02.598845+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -10383,9 +10383,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
"ambiguous_runtime": 3
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 32,
@@ -10398,8 +10398,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
"total": 3,
"unresolvedFailureCount": 3
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|muse_glimmer|none|34": {
"attributableFailureCount": 1,
@@ -16201,17 +16201,17 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 2361,
"totalRecords": 2464,
"terminalRecords": 2363,
"totalRecords": 2466,
"totals": {
"attributableFailureCount": 773,
"decisionFailureRate": 0.8145,
"decisionSuccessRate": 0.1855,
"decisionTotal": 949,
"attributableFailureCount": 774,
"decisionFailureRate": 0.8147,
"decisionSuccessRate": 0.1853,
"decisionTotal": 950,
"failureBreakdown": {
"ambiguous_runtime": 595,
"ambiguous_runtime": 596,
"backend_operator": 55,
"framework_architecture_unsupported": 519,
"framework_architecture_unsupported": 520,
"memory_capacity": 12,
"model_load": 89,
"platform_infrastructure": 11,
@@ -16221,18 +16221,18 @@
"参数/模板问题": 133,
"验证失败": 673
},
"failureCount": 2185,
"failureCount": 2187,
"failureRate": 0.9255,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 11,
"successCount": 176,
"successRate": 0.0745,
"total": 2361,
"unresolvedFailureCount": 1401
"total": 2363,
"unresolvedFailureCount": 1402
},
"warnings": [
"GPU Iluvatar_bi-150 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 Ascend_910-b3 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。",
@@ -16243,7 +16243,7 @@
"GPU Sunrise_pt-200-x1 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 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-150 本地统计失败率偏高（≥50%），建议重点关注。",
"组合 MetaX_c-500|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 Ascend_910-b4|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。",
"组合 Iluvatar_mrv-100|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -16268,6 +16268,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 2464,
"summarizedRecords": 2466,
"version": 1
}