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

state: generation 5099 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-10 09:40:41 +00:00
parent 42d120a116
commit 18effa64e0
10 changed files with 3064 additions and 2728 deletions
Download Patch File Download Diff File Expand all files Collapse all files

130
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-10T09:29:58.731302+00:00",
"lastSyncTime": "2026-09-10T09:29:56.132283+00:00",
"generatedAt": "2026-09-10T09:38:19.296061+00:00",
"lastSyncTime": "2026-09-10T09:38:19.106782+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1872,10 +1872,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 27,
"ambiguous_runtime": 28,
"参数/模板问题": 1
},
"failureCount": 28,
"failureCount": 29,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -1885,8 +1885,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 28,
"unresolvedFailureCount": 28
"total": 29,
"unresolvedFailureCount": 29
},
"MetaX_c-500|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -2411,22 +2411,22 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 32,
"failureBreakdown": {
"ambiguous_runtime": 28,
"ambiguous_runtime": 29,
"framework_architecture_unsupported": 4,
"model_load": 1,
"platform_infrastructure": 1,
"tokenizer_compatibility": 27,
"参数/模板问题": 7
},
"failureCount": 68,
"failureCount": 69,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 0,
"successRate": 0.0,
"total": 68,
"unresolvedFailureCount": 35
"total": 69,
"unresolvedFailureCount": 36
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 0,
@@ -2447,7 +2447,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T09:29:58.725727+00:00",
"generatedAt": "2026-09-10T09:38:19.291073+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2638,20 +2638,20 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 59,
"ambiguous_runtime": 60,
"memory_capacity": 1,
"参数/模板问题": 1,
"验证失败": 23
},
"failureCount": 84,
"failureCount": 85,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 84,
"unresolvedFailureCount": 83
"total": 85,
"unresolvedFailureCount": 84
},
"MetaX_c-500": {
"attributableFailureCount": 42,
@@ -3455,6 +3455,29 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|rwkv7|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": "rwkv7",
"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|starcoder2|compressed-tensors": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -4336,13 +4359,13 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 13
"ambiguous_runtime": 14
},
"failureCount": 13,
"failureCount": 14,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-09T14:21:21.949441+00:00",
"lastTerminalAt": "2026-09-10T09:38:19.106782+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4350,8 +4373,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 13,
"unresolvedFailureCount": 13
"total": 14,
"unresolvedFailureCount": 14
},
"MetaX_c-500|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -5114,6 +5137,31 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|rwkv7|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastTerminalAt": "2026-09-10T09:38:19.106782+00:00",
"modelType": "rwkv7",
"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|starcoder2|compressed-tensors": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -6195,6 +6243,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|rwkv7|none|31": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 31,
"modelType": "rwkv7",
"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|starcoder2|compressed-tensors|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -6986,15 +7058,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1550,
"totalRecords": 1637,
"terminalRecords": 1551,
"totalRecords": 1638,
"totals": {
"attributableFailureCount": 405,
"decisionFailureRate": 0.8882,
"decisionSuccessRate": 0.1118,
"decisionTotal": 456,
"failureBreakdown": {
"ambiguous_runtime": 324,
"ambiguous_runtime": 325,
"backend_operator": 34,
"framework_architecture_unsupported": 271,
"memory_capacity": 11,
@@ -7006,21 +7078,21 @@
"参数/模板问题": 95,
"验证失败": 673
},
"failureCount": 1499,
"failureCount": 1500,
"failureRate": 0.9671,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 51,
"successRate": 0.0329,
"total": 1550,
"unresolvedFailureCount": 1092
"total": 1551,
"unresolvedFailureCount": 1093
},
"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。",
@@ -7028,7 +7100,7 @@
"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。",
@@ -7049,6 +7121,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1637,
"summarizedRecords": 1638,
"version": 1
}