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

state: generation 5248 (intent)

Browse Source
This commit is contained in:
CoolBoy
2026-09-10 16:07:12 +00:00
parent 3db912f3be
commit c905343ac1
7 changed files with 834 additions and 833 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": "2026-09-10T15:56:47.793655+00:00",
"lastSyncTime": "2026-09-10T15:56:47.546297+00:00",
"generatedAt": "2026-09-10T16:05:32.108357+00:00",
"lastSyncTime": "2026-09-10T16:05:31.804365+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2045,17 +2045,17 @@
"unresolvedFailureCount": 33
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 34,
"attributableFailureCount": 35,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 34,
"decisionTotal": 35,
"failureBreakdown": {
"framework_architecture_unsupported": 2,
"platform_infrastructure": 2,
"tokenizer_compatibility": 32,
"tokenizer_compatibility": 33,
"参数/模板问题": 6
},
"failureCount": 42,
"failureCount": 43,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -2065,7 +2065,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 42,
"total": 43,
"unresolvedFailureCount": 6
},
"Sunrise_pt-200-x1|vllm|text-generation": {
@@ -2143,12 +2143,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 44,
"failureBreakdown": {
"ambiguous_runtime": 56,
"ambiguous_runtime": 57,
"framework_architecture_unsupported": 38,
"memory_capacity": 1,
"model_load": 5
},
"failureCount": 100,
"failureCount": 101,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2158,8 +2158,8 @@
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 100,
"unresolvedFailureCount": 56
"total": 101,
"unresolvedFailureCount": 57
},
"hygon_k100-ai|llamacpp|text-generation": {
"attributableFailureCount": 0,
@@ -2321,7 +2321,7 @@
"decisionSuccessRate": 0.0083,
"decisionTotal": 242,
"failureBreakdown": {
"ambiguous_runtime": 174,
"ambiguous_runtime": 175,
"backend_operator": 33,
"framework_architecture_unsupported": 169,
"memory_capacity": 6,
@@ -2332,15 +2332,15 @@
"tokenizer_compatibility": 3,
"参数/模板问题": 24
},
"failureCount": 439,
"failureCount": 440,
"failureRate": 0.9955,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 2,
"successRate": 0.0045,
"total": 441,
"unresolvedFailureCount": 198
"total": 442,
"unresolvedFailureCount": 199
},
"vllm-mlu": {
"attributableFailureCount": 7,
@@ -2402,26 +2402,26 @@
"unresolvedFailureCount": 4
},
"vllm_fix_tokenizer": {
"attributableFailureCount": 37,
"attributableFailureCount": 38,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 37,
"decisionTotal": 38,
"failureBreakdown": {
"ambiguous_runtime": 34,
"framework_architecture_unsupported": 4,
"model_load": 1,
"platform_infrastructure": 2,
"tokenizer_compatibility": 32,
"tokenizer_compatibility": 33,
"参数/模板问题": 7
},
"failureCount": 80,
"failureCount": 81,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 0,
"successRate": 0.0,
"total": 80,
"total": 81,
"unresolvedFailureCount": 41
},
"vllm_tokenizer_patch": {
@@ -2443,7 +2443,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T15:56:47.789236+00:00",
"generatedAt": "2026-09-10T16:05:32.103753+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2700,26 +2700,26 @@
"unresolvedFailureCount": 63
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 35,
"decisionFailureRate": 0.9722,
"decisionSuccessRate": 0.0278,
"decisionTotal": 36,
"attributableFailureCount": 36,
"decisionFailureRate": 0.973,
"decisionSuccessRate": 0.027,
"decisionTotal": 37,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 3,
"platform_infrastructure": 3,
"tokenizer_compatibility": 32,
"tokenizer_compatibility": 33,
"参数/模板问题": 9,
"验证失败": 32
},
"failureCount": 80,
"failureRate": 0.9877,
"failureCount": 81,
"failureRate": 0.9878,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 3,
"successCount": 1,
"successRate": 0.0123,
"total": 81,
"successRate": 0.0122,
"total": 82,
"unresolvedFailureCount": 42
},
"Vastai_va16": {
@@ -2728,22 +2728,22 @@
"decisionSuccessRate": 0.2167,
"decisionTotal": 60,
"failureBreakdown": {
"ambiguous_runtime": 57,
"ambiguous_runtime": 58,
"framework_architecture_unsupported": 40,
"memory_capacity": 1,
"model_load": 6,
"参数/模板问题": 13,
"验证失败": 130
},
"failureCount": 247,
"failureRate": 0.95,
"failureCount": 248,
"failureRate": 0.9502,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 13,
"successRate": 0.05,
"total": 260,
"unresolvedFailureCount": 200
"successRate": 0.0498,
"total": 261,
"unresolvedFailureCount": 201
},
"hygon_k100-ai": {
"attributableFailureCount": 39,
@@ -4448,22 +4448,22 @@
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 13,
"consecutiveFailures": 13,
"attributableFailureCount": 14,
"consecutiveFailures": 14,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 13,
"decisionTotal": 14,
"failureBreakdown": {
"framework_architecture_unsupported": 1,
"platform_infrastructure": 2,
"tokenizer_compatibility": 12
"tokenizer_compatibility": 13
},
"failureCount": 15,
"failureCount": 16,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": "2026-09-10T11:01:21+00:00",
"lastTerminalAt": "2026-09-10T11:48:57.307255+00:00",
"lastTerminalAt": "2026-09-10T16:05:31.804335+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
@@ -4471,7 +4471,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 15,
"total": 16,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation": {
@@ -4539,7 +4539,7 @@
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T12:32:29.847014+00:00",
"lastTerminalAt": "2026-09-10T16:05:31.804365+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4583,13 +4583,13 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 7,
"failureBreakdown": {
"ambiguous_runtime": 13,
"ambiguous_runtime": 12,
"framework_architecture_unsupported": 4,
"model_load": 1,
"repository_structure": 1,
"runtime_memory": 1
},
"failureCount": 20,
"failureCount": 19,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -4601,8 +4601,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 13
"total": 19,
"unresolvedFailureCount": 12
}
},
"recentProfileCombinationStats": {
@@ -7121,15 +7121,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1603,
"totalRecords": 1690,
"terminalRecords": 1605,
"totalRecords": 1692,
"totals": {
"attributableFailureCount": 420,
"decisionFailureRate": 0.8898,
"decisionSuccessRate": 0.1102,
"decisionTotal": 472,
"attributableFailureCount": 421,
"decisionFailureRate": 0.8901,
"decisionSuccessRate": 0.1099,
"decisionTotal": 473,
"failureBreakdown": {
"ambiguous_runtime": 357,
"ambiguous_runtime": 358,
"backend_operator": 40,
"framework_architecture_unsupported": 272,
"memory_capacity": 11,
@@ -7137,35 +7137,34 @@
"platform_infrastructure": 3,
"repository_structure": 5,
"runtime_memory": 6,
"tokenizer_compatibility": 38,
"tokenizer_compatibility": 39,
"参数/模板问题": 98,
"验证失败": 673
},
"failureCount": 1551,
"failureCount": 1553,
"failureRate": 0.9676,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 3,
"successCount": 52,
"successRate": 0.0324,
"total": 1603,
"unresolvedFailureCount": 1128
"total": 1605,
"unresolvedFailureCount": 1129
},
"warnings": [
"GPU Ascend_910-b3 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 Iluvatar_mrv-100 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 Mthreads_s4000 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 MetaX_c-500 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 Iluvatar_bi-150 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 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 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 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。",
"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-x4|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 Mthreads_s4000|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 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 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -7180,10 +7179,11 @@
"组合 hygon_k100-ai|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 Iluvatar_bi-150|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|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-x4|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 hygon_k100-ai|vllm-patch-tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。"
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1690,
"summarizedRecords": 1692,
"version": 1
}