state: generation 6894 (cycle)

This commit is contained in:
2026-09-13 21:29:16 +00:00
parent 24097daae5
commit 9a2ff4c040
10 changed files with 2659 additions and 2605 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-13T21:18:48.937127+00:00",
"lastSyncTime": "2026-09-13T21:18:48.715311+00:00",
"generatedAt": "2026-09-13T21:27:15.319333+00:00",
"lastSyncTime": "2026-09-13T21:27:15.041934+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2254,18 +2254,18 @@
"unresolvedFailureCount": 34
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 49,
"attributableFailureCount": 50,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 49,
"decisionTotal": 50,
"failureBreakdown": {
"backend_operator": 2,
"framework_architecture_unsupported": 6,
"platform_infrastructure": 4,
"tokenizer_compatibility": 41,
"tokenizer_compatibility": 42,
"参数/模板问题": 6
},
"failureCount": 59,
"failureCount": 60,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -2275,22 +2275,23 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 59,
"total": 60,
"unresolvedFailureCount": 6
},
"Sunrise_pt-200-x1|vllm|text-generation": {
"attributableFailureCount": 6,
"attributableFailureCount": 7,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 6,
"decisionTotal": 7,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 2,
"memory_capacity": 1,
"platform_infrastructure": 1,
"tokenizer_compatibility": 4,
"参数/模板问题": 2
},
"failureCount": 10,
"failureCount": 11,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2300,7 +2301,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 10,
"total": 11,
"unresolvedFailureCount": 3
},
"Vastai_va16|unknown|text-generation": {
@@ -2529,15 +2530,15 @@
"unresolvedFailureCount": 877
},
"vllm": {
"attributableFailureCount": 301,
"decisionFailureRate": 0.9901,
"decisionSuccessRate": 0.0099,
"decisionTotal": 304,
"attributableFailureCount": 302,
"decisionFailureRate": 0.9902,
"decisionSuccessRate": 0.0098,
"decisionTotal": 305,
"failureBreakdown": {
"ambiguous_runtime": 201,
"backend_operator": 34,
"framework_architecture_unsupported": 214,
"memory_capacity": 6,
"memory_capacity": 7,
"model_load": 26,
"platform_infrastructure": 1,
"repository_structure": 8,
@@ -2545,14 +2546,14 @@
"tokenizer_compatibility": 7,
"参数/模板问题": 24
},
"failureCount": 527,
"failureRate": 0.9943,
"failureCount": 528,
"failureRate": 0.9944,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 3,
"successRate": 0.0057,
"total": 530,
"successRate": 0.0056,
"total": 531,
"unresolvedFailureCount": 225
},
"vllm-mlu": {
@@ -2615,27 +2616,27 @@
"unresolvedFailureCount": 4
},
"vllm_fix_tokenizer": {
"attributableFailureCount": 52,
"attributableFailureCount": 53,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 52,
"decisionTotal": 53,
"failureBreakdown": {
"ambiguous_runtime": 37,
"backend_operator": 2,
"framework_architecture_unsupported": 8,
"model_load": 1,
"platform_infrastructure": 4,
"tokenizer_compatibility": 41,
"tokenizer_compatibility": 42,
"参数/模板问题": 7
},
"failureCount": 100,
"failureCount": 101,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 0,
"successRate": 0.0,
"total": 100,
"total": 101,
"unresolvedFailureCount": 44
},
"vllm_tokenizer_patch": {
@@ -2657,7 +2658,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-13T21:18:48.933122+00:00",
"generatedAt": "2026-09-13T21:27:15.315167+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 31,
@@ -2917,27 +2918,28 @@
"unresolvedFailureCount": 77
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 55,
"decisionFailureRate": 0.9821,
"decisionSuccessRate": 0.0179,
"decisionTotal": 56,
"attributableFailureCount": 57,
"decisionFailureRate": 0.9828,
"decisionSuccessRate": 0.0172,
"decisionTotal": 58,
"failureBreakdown": {
"ambiguous_runtime": 1,
"backend_operator": 2,
"framework_architecture_unsupported": 8,
"memory_capacity": 1,
"platform_infrastructure": 5,
"tokenizer_compatibility": 45,
"tokenizer_compatibility": 46,
"参数/模板问题": 10,
"验证失败": 32
},
"failureCount": 103,
"failureRate": 0.9904,
"failureCount": 105,
"failureRate": 0.9906,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 5,
"successCount": 1,
"successRate": 0.0096,
"total": 104,
"successRate": 0.0094,
"total": 106,
"unresolvedFailureCount": 43
},
"Vastai_va16": {
@@ -2999,6 +3001,7 @@
"Kunlunxin_p-800": 100.0,
"MetaX_c-500": 64.0,
"Mthreads_s4000": 48.0,
"Sunrise_pt-200-x1": 64.0,
"Vastai_va16": 32.0,
"hygon_k100-ai": 64.0
},
@@ -4383,6 +4386,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"tokenizer_compatibility": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "starcoder2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation|llama|compressed-tensors": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -4990,24 +5016,24 @@
"consecutiveFailures": 0,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"参数/模板问题": 1
},
"failureCount": 1,
"failureRate": 0.5,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-13T02:55:29.910704+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.5,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 2,
"total": 1,
"unresolvedFailureCount": 1
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
@@ -5038,22 +5064,23 @@
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation": {
"attributableFailureCount": 4,
"consecutiveFailures": 4,
"attributableFailureCount": 5,
"consecutiveFailures": 5,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 4,
"decisionTotal": 5,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 1,
"memory_capacity": 1,
"tokenizer_compatibility": 3
},
"failureCount": 5,
"failureCount": 6,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-13T21:09:24.912775+00:00",
"lastTerminalAt": "2026-09-13T21:27:15.041934+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -5061,7 +5088,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 5,
"total": 6,
"unresolvedFailureCount": 1
},
"Vastai_va16|vllm|text-generation": {
@@ -7400,6 +7427,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"tokenizer_compatibility": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 34,
"modelType": "starcoder2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation|llama|compressed-tensors|30": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -7641,34 +7692,34 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1786,
"totalRecords": 1879,
"terminalRecords": 1788,
"totalRecords": 1881,
"totals": {
"attributableFailureCount": 528,
"decisionFailureRate": 0.8995,
"decisionSuccessRate": 0.1005,
"decisionTotal": 587,
"attributableFailureCount": 530,
"decisionFailureRate": 0.8998,
"decisionSuccessRate": 0.1002,
"decisionTotal": 589,
"failureBreakdown": {
"ambiguous_runtime": 417,
"backend_operator": 43,
"framework_architecture_unsupported": 335,
"memory_capacity": 11,
"memory_capacity": 12,
"model_load": 74,
"platform_infrastructure": 6,
"repository_structure": 8,
"runtime_memory": 6,
"tokenizer_compatibility": 51,
"tokenizer_compatibility": 52,
"参数/模板问题": 103,
"验证失败": 673
},
"failureCount": 1727,
"failureCount": 1729,
"failureRate": 0.967,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 6,
"successCount": 59,
"successRate": 0.033,
"total": 1786,
"total": 1788,
"unresolvedFailureCount": 1193
},
"warnings": [
@@ -7707,6 +7758,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1879,
"summarizedRecords": 1881,
"version": 1
}