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

state: generation 6332 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-12 19:03:59 +00:00
parent 94854846a5
commit cd6fe88754
11 changed files with 2297 additions and 2210 deletions
Download Patch File Download Diff File Expand all files Collapse all files

198
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,9 +1,30 @@
{
"generatedAt": "2026-09-12T18:04:41.740562+00:00",
"lastSyncTime": "2026-09-12T18:04:41.532609+00:00",
"generatedAt": "2026-09-12T18:59:53.566932+00:00",
"lastSyncTime": "2026-09-12T18:59:53.316571+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
"ascend_910-b3|vllm|text-generation|architectures:spark2_5forcausallm": {
"architectureSignature": "architectures:spark2_5forcausallm",
"architectures": [
"spark2_5forcausallm"
],
"evidenceCount": 1,
"expiresAt": "2026-10-12T18:53:21+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-12T18:53:21+00:00",
"latestSuccessfulAt": null,
"matchType": "architectures",
"modelType": null,
"sourceModelIds": [
"XHToken/Spark-X2.5-4B"
],
"sourceTaskIds": [
"4549470"
],
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation"
},
"ascend_910-b3|vllm|text-generation|model_type:glm_ocr": {
"architectureSignature": "model_type:glm_ocr",
"architectures": [],
@@ -1411,9 +1432,9 @@
}
},
"architectureCompatibilitySummary": {
"activeBlockCount": 71,
"activeBlockCount": 72,
"byGpuFramework": {
"Ascend_910-b3|vllm": 8,
"Ascend_910-b3|vllm": 9,
"Ascend_910-b4|vllm": 10,
"Cambricon_mlu-370-x8|vllm": 2,
"Cambricon_mlu-370-x8|vllm-mlu": 5,
@@ -1474,17 +1495,17 @@
"unresolvedFailureCount": 1
},
"Ascend_910-b3|vllm|text-generation": {
"attributableFailureCount": 28,
"attributableFailureCount": 29,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 28,
"decisionTotal": 29,
"failureBreakdown": {
"ambiguous_runtime": 28,
"framework_architecture_unsupported": 26,
"framework_architecture_unsupported": 27,
"memory_capacity": 1,
"tokenizer_compatibility": 1
},
"failureCount": 56,
"failureCount": 57,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -1494,7 +1515,7 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 56,
"total": 57,
"unresolvedFailureCount": 28
},
"Ascend_910-b4|llamacpp|text-generation": {
@@ -2327,15 +2348,15 @@
"unresolvedFailureCount": 28
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation": {
"attributableFailureCount": 3,
"attributableFailureCount": 4,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 3,
"decisionTotal": 4,
"failureBreakdown": {
"framework_architecture_unsupported": 3,
"framework_architecture_unsupported": 4,
"参数/模板问题": 8
},
"failureCount": 11,
"failureCount": 12,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"pendingCount": 0,
@@ -2345,7 +2366,7 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 11,
"total": 12,
"unresolvedFailureCount": 8
},
"hygon_k100-ai|vllm|text-generation": {
@@ -2440,14 +2461,14 @@
"unresolvedFailureCount": 866
},
"vllm": {
"attributableFailureCount": 280,
"attributableFailureCount": 281,
"decisionFailureRate": 0.9894,
"decisionSuccessRate": 0.0106,
"decisionTotal": 283,
"decisionTotal": 284,
"failureBreakdown": {
"ambiguous_runtime": 200,
"backend_operator": 34,
"framework_architecture_unsupported": 194,
"framework_architecture_unsupported": 195,
"memory_capacity": 6,
"model_load": 26,
"platform_infrastructure": 1,
@@ -2456,14 +2477,14 @@
"tokenizer_compatibility": 6,
"参数/模板问题": 24
},
"failureCount": 505,
"failureCount": 506,
"failureRate": 0.9941,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 3,
"successRate": 0.0059,
"total": 508,
"total": 509,
"unresolvedFailureCount": 224
},
"vllm-mlu": {
@@ -2487,22 +2508,22 @@
"unresolvedFailureCount": 22
},
"vllm-patch-tokenizer": {
"attributableFailureCount": 3,
"attributableFailureCount": 4,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 3,
"decisionTotal": 4,
"failureBreakdown": {
"framework_architecture_unsupported": 3,
"framework_architecture_unsupported": 4,
"参数/模板问题": 8
},
"failureCount": 11,
"failureCount": 12,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 11,
"total": 12,
"unresolvedFailureCount": 8
},
"vllm_0_17_0_corex_4_4_0": {
@@ -2568,29 +2589,29 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-12T18:04:41.736777+00:00",
"generatedAt": "2026-09-12T18:59:53.563039+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 28,
"decisionFailureRate": 0.9655,
"decisionSuccessRate": 0.0345,
"decisionTotal": 29,
"attributableFailureCount": 29,
"decisionFailureRate": 0.9667,
"decisionSuccessRate": 0.0333,
"decisionTotal": 30,
"failureBreakdown": {
"ambiguous_runtime": 28,
"framework_architecture_unsupported": 26,
"framework_architecture_unsupported": 27,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"参数/模板问题": 8,
"验证失败": 27
},
"failureCount": 91,
"failureRate": 0.9891,
"failureCount": 92,
"failureRate": 0.9892,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0109,
"total": 92,
"successRate": 0.0108,
"total": 93,
"unresolvedFailureCount": 63
},
"Ascend_910-b4": {
@@ -2875,13 +2896,13 @@
"unresolvedFailureCount": 206
},
"hygon_k100-ai": {
"attributableFailureCount": 45,
"attributableFailureCount": 46,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 45,
"decisionTotal": 46,
"failureBreakdown": {
"ambiguous_runtime": 20,
"framework_architecture_unsupported": 34,
"framework_architecture_unsupported": 35,
"memory_capacity": 1,
"model_load": 4,
"repository_structure": 4,
@@ -2889,14 +2910,14 @@
"参数/模板问题": 9,
"验证失败": 27
},
"failureCount": 101,
"failureCount": 102,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 101,
"total": 102,
"unresolvedFailureCount": 56
}
},
@@ -4294,6 +4315,29 @@
"total": 2,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|rwkv7|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"modelType": "rwkv7",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|zaya|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -4320,21 +4364,21 @@
},
"recentCombinationStats": {
"Ascend_910-b3|vllm|text-generation": {
"attributableFailureCount": 2,
"consecutiveFailures": 2,
"attributableFailureCount": 3,
"consecutiveFailures": 3,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"decisionTotal": 3,
"failureBreakdown": {
"ambiguous_runtime": 18,
"framework_architecture_unsupported": 2
"ambiguous_runtime": 17,
"framework_architecture_unsupported": 3
},
"failureCount": 20,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-12T14:41:33.434355+00:00",
"lastTerminalAt": "2026-09-12T18:59:53.316516+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4343,7 +4387,7 @@
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 18
"unresolvedFailureCount": 17
},
"Ascend_910-b4|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -4614,9 +4658,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 12
"ambiguous_runtime": 11
},
"failureCount": 12,
"failureCount": 11,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": null,
@@ -4628,8 +4672,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 12,
"unresolvedFailureCount": 12
"total": 11,
"unresolvedFailureCount": 11
},
"MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 6,
@@ -4952,9 +4996,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 3
"ambiguous_runtime": 2
},
"failureCount": 3,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastTerminalAt": "2026-09-10T02:58:51.546388+00:00",
@@ -4967,8 +5011,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 3,
"unresolvedFailureCount": 3
"total": 2,
"unresolvedFailureCount": 2
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_mtp|none": {
"attributableFailureCount": 0,
@@ -7276,6 +7320,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|rwkv7|none|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"loadSizeLog2Bucket": 32,
"modelType": "rwkv7",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|zaya|none|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -7301,17 +7369,17 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1732,
"totalRecords": 1819,
"terminalRecords": 1734,
"totalRecords": 1821,
"totals": {
"attributableFailureCount": 492,
"decisionFailureRate": 0.8962,
"decisionSuccessRate": 0.1038,
"decisionTotal": 549,
"attributableFailureCount": 494,
"decisionFailureRate": 0.8966,
"decisionSuccessRate": 0.1034,
"decisionTotal": 551,
"failureBreakdown": {
"ambiguous_runtime": 405,
"backend_operator": 42,
"framework_architecture_unsupported": 305,
"framework_architecture_unsupported": 307,
"memory_capacity": 11,
"model_load": 72,
"platform_infrastructure": 4,
@@ -7321,20 +7389,21 @@
"参数/模板问题": 101,
"验证失败": 673
},
"failureCount": 1675,
"failureCount": 1677,
"failureRate": 0.9671,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 57,
"successRate": 0.0329,
"total": 1732,
"total": 1734,
"unresolvedFailureCount": 1179
},
"warnings": [
"GPU Ascend_910-b3 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 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 Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -7343,7 +7412,6 @@
"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。",
"GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
"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。",
"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 Ascend_910-b4|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -7366,6 +7434,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1819,
"summarizedRecords": 1821,
"version": 1
}