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

state: generation 5072 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-10 08:21:40 +00:00
parent 23b2de2ba2
commit 241d348805
10 changed files with 2270 additions and 2228 deletions
Download Patch File Download Diff File Expand all files Collapse all files

163
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-10T08:10:58.477072+00:00",
"lastSyncTime": "2026-09-10T08:10:58.225916+00:00",
"generatedAt": "2026-09-10T08:19:33.977040+00:00",
"lastSyncTime": "2026-09-10T08:19:33.742658+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1576,25 +1576,25 @@
"decisionSuccessRate": 0.2222,
"decisionTotal": 9,
"failureBreakdown": {
"ambiguous_runtime": 18,
"ambiguous_runtime": 19,
"framework_architecture_unsupported": 5,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"参数/模板问题": 5,
"验证失败": 22
},
"failureCount": 52,
"failureRate": 0.963,
"failureCount": 53,
"failureRate": 0.9636,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.037,
"successRate": 0.0364,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 54,
"unresolvedFailureCount": 45
"total": 55,
"unresolvedFailureCount": 46
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
"attributableFailureCount": 7,
@@ -1750,25 +1750,25 @@
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation": {
"attributableFailureCount": 4,
"decisionFailureRate": 0.8,
"decisionSuccessRate": 0.2,
"decisionTotal": 5,
"decisionFailureRate": 0.6667,
"decisionSuccessRate": 0.3333,
"decisionTotal": 6,
"failureBreakdown": {
"ambiguous_runtime": 3,
"backend_operator": 3,
"framework_architecture_unsupported": 1
},
"failureCount": 7,
"failureRate": 0.875,
"failureRate": 0.7778,
"framework": "vllm_0_17_0_corex_4_4_0",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.125,
"successCount": 2,
"successRate": 0.2222,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 8,
"total": 9,
"unresolvedFailureCount": 3
},
"Iluvatar_bi-150|vllm|text-generation": {
@@ -2300,7 +2300,7 @@
"decisionSuccessRate": 0.284,
"decisionTotal": 169,
"failureBreakdown": {
"ambiguous_runtime": 112,
"ambiguous_runtime": 113,
"backend_operator": 2,
"framework_architecture_unsupported": 87,
"memory_capacity": 5,
@@ -2309,15 +2309,15 @@
"参数/模板问题": 56,
"验证失败": 673
},
"failureCount": 962,
"failureCount": 963,
"failureRate": 0.9525,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 48,
"successRate": 0.0475,
"total": 1010,
"unresolvedFailureCount": 841
"total": 1011,
"unresolvedFailureCount": 842
},
"vllm": {
"attributableFailureCount": 231,
@@ -2387,22 +2387,22 @@
},
"vllm_0_17_0_corex_4_4_0": {
"attributableFailureCount": 4,
"decisionFailureRate": 0.8,
"decisionSuccessRate": 0.2,
"decisionTotal": 5,
"decisionFailureRate": 0.6667,
"decisionSuccessRate": 0.3333,
"decisionTotal": 6,
"failureBreakdown": {
"ambiguous_runtime": 3,
"backend_operator": 3,
"framework_architecture_unsupported": 1
},
"failureCount": 7,
"failureRate": 0.875,
"failureRate": 0.7778,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.125,
"total": 8,
"successCount": 2,
"successRate": 0.2222,
"total": 9,
"unresolvedFailureCount": 3
},
"vllm_fix_tokenizer": {
@@ -2447,7 +2447,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T08:10:58.472731+00:00",
"generatedAt": "2026-09-10T08:19:33.972825+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2549,22 +2549,22 @@
"decisionSuccessRate": 0.1053,
"decisionTotal": 19,
"failureBreakdown": {
"ambiguous_runtime": 32,
"ambiguous_runtime": 33,
"framework_architecture_unsupported": 15,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"参数/模板问题": 18,
"验证失败": 22
},
"failureCount": 89,
"failureRate": 0.978,
"failureCount": 90,
"failureRate": 0.9783,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.022,
"total": 91,
"unresolvedFailureCount": 72
"successRate": 0.0217,
"total": 92,
"unresolvedFailureCount": 73
},
"Iluvatar_bi-100": {
"attributableFailureCount": 0,
@@ -2587,9 +2587,9 @@
},
"Iluvatar_bi-150": {
"attributableFailureCount": 19,
"decisionFailureRate": 0.76,
"decisionSuccessRate": 0.24,
"decisionTotal": 25,
"decisionFailureRate": 0.7308,
"decisionSuccessRate": 0.2692,
"decisionTotal": 26,
"failureBreakdown": {
"ambiguous_runtime": 11,
"backend_operator": 5,
@@ -2600,13 +2600,13 @@
"验证失败": 30
},
"failureCount": 61,
"failureRate": 0.9104,
"failureRate": 0.8971,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 6,
"successRate": 0.0896,
"total": 67,
"successCount": 7,
"successRate": 0.1029,
"total": 68,
"unresolvedFailureCount": 42
},
"Iluvatar_mrv-100": {
@@ -3181,6 +3181,27 @@
"total": 4,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|phi3|compressed-tensors": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"modelType": "phi3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 1,
"successRate": 1.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|rwkv7|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -4082,15 +4103,15 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"failureBreakdown": {
"ambiguous_runtime": 14,
"ambiguous_runtime": 15,
"framework_architecture_unsupported": 1,
"tokenizer_compatibility": 1
},
"failureCount": 16,
"failureCount": 17,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T07:53:10.699377+00:00",
"lastTerminalAt": "2026-09-10T08:19:33.742658+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4098,8 +4119,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 16,
"unresolvedFailureCount": 14
"total": 17,
"unresolvedFailureCount": 15
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
"attributableFailureCount": 4,
@@ -5768,6 +5789,28 @@
"total": 2,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|phi3|compressed-tensors|33": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"loadSizeLog2Bucket": 33,
"modelType": "phi3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 1,
"successRate": 1.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|rwkv7|none|31": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -6943,15 +6986,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1537,
"totalRecords": 1624,
"terminalRecords": 1539,
"totalRecords": 1626,
"totals": {
"attributableFailureCount": 401,
"decisionFailureRate": 0.8891,
"decisionSuccessRate": 0.1109,
"decisionTotal": 451,
"decisionFailureRate": 0.8872,
"decisionSuccessRate": 0.1128,
"decisionTotal": 452,
"failureBreakdown": {
"ambiguous_runtime": 316,
"ambiguous_runtime": 317,
"backend_operator": 30,
"framework_architecture_unsupported": 271,
"memory_capacity": 11,
@@ -6963,21 +7006,21 @@
"参数/模板问题": 95,
"验证失败": 673
},
"failureCount": 1487,
"failureRate": 0.9675,
"failureCount": 1488,
"failureRate": 0.9669,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 50,
"successRate": 0.0325,
"total": 1537,
"unresolvedFailureCount": 1084
"successCount": 51,
"successRate": 0.0331,
"total": 1539,
"unresolvedFailureCount": 1085
},
"warnings": [
"GPU Cambricon_mlu-370-x8 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 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 Iluvatar_bi-150 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。",
@@ -6985,7 +7028,7 @@
"GPU hygon_k100-ai 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 Mthreads_s4000 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 Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
"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。",
"组合 Cambricon_mlu-370-x8|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 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。",
@@ -7006,6 +7049,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1624,
"summarizedRecords": 1626,
"version": 1
}