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

state: generation 5125 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-10 10:50:21 +00:00
parent dfc95341ee
commit 7733d48c8b
9 changed files with 3291 additions and 3048 deletions
Download Patch File Download Diff File Expand all files Collapse all files

106
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-10T10:30:02.798435+00:00",
"lastSyncTime": "2026-09-10T10:30:02.547307+00:00",
"generatedAt": "2026-09-10T10:46:39.673314+00:00",
"lastSyncTime": "2026-09-10T10:46:39.406893+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -584,7 +584,7 @@
"hygon_k100-ai|vllm|text-generation|model_type:qwen3_5_moe": {
"architectureSignature": "model_type:qwen3_5_moe",
"architectures": [],
"evidenceCount": 2,
"evidenceCount": 1,
"expiresAt": "2026-10-07T23:51:21+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-07T23:51:21+00:00",
@@ -592,12 +592,10 @@
"matchType": "model_type",
"modelType": "qwen3_5_moe",
"sourceModelIds": [
"mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B",
"mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B"
"mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B"
],
"sourceTaskIds": [
"4479115",
"4482387"
"4479115"
],
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation"
@@ -2050,17 +2048,17 @@
"unresolvedFailureCount": 33
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 29,
"attributableFailureCount": 30,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 29,
"decisionTotal": 30,
"failureBreakdown": {
"framework_architecture_unsupported": 2,
"platform_infrastructure": 1,
"tokenizer_compatibility": 27,
"tokenizer_compatibility": 28,
"参数/模板问题": 6
},
"failureCount": 36,
"failureCount": 37,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -2070,7 +2068,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 36,
"total": 37,
"unresolvedFailureCount": 6
},
"Sunrise_pt-200-x1|vllm|text-generation": {
@@ -2406,26 +2404,26 @@
"unresolvedFailureCount": 3
},
"vllm_fix_tokenizer": {
"attributableFailureCount": 32,
"attributableFailureCount": 33,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 32,
"decisionTotal": 33,
"failureBreakdown": {
"ambiguous_runtime": 29,
"framework_architecture_unsupported": 4,
"model_load": 1,
"platform_infrastructure": 1,
"tokenizer_compatibility": 27,
"tokenizer_compatibility": 28,
"参数/模板问题": 7
},
"failureCount": 69,
"failureCount": 70,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 0,
"successRate": 0.0,
"total": 69,
"total": 70,
"unresolvedFailureCount": 36
},
"vllm_tokenizer_patch": {
@@ -2447,7 +2445,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T10:30:02.793656+00:00",
"generatedAt": "2026-09-10T10:46:39.668682+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2704,25 +2702,25 @@
"unresolvedFailureCount": 59
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 30,
"decisionFailureRate": 0.9677,
"decisionSuccessRate": 0.0323,
"decisionTotal": 31,
"attributableFailureCount": 31,
"decisionFailureRate": 0.9688,
"decisionSuccessRate": 0.0312,
"decisionTotal": 32,
"failureBreakdown": {
"framework_architecture_unsupported": 3,
"platform_infrastructure": 2,
"tokenizer_compatibility": 27,
"tokenizer_compatibility": 28,
"参数/模板问题": 9,
"验证失败": 32
},
"failureCount": 73,
"failureRate": 0.9865,
"failureCount": 74,
"failureRate": 0.9867,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 1,
"successRate": 0.0135,
"total": 74,
"successRate": 0.0133,
"total": 75,
"unresolvedFailureCount": 41
},
"Vastai_va16": {
@@ -4503,22 +4501,22 @@
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 8,
"consecutiveFailures": 8,
"attributableFailureCount": 9,
"consecutiveFailures": 9,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 8,
"decisionTotal": 9,
"failureBreakdown": {
"framework_architecture_unsupported": 1,
"platform_infrastructure": 1,
"tokenizer_compatibility": 7
"tokenizer_compatibility": 8
},
"failureCount": 9,
"failureCount": 10,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": "2026-09-08T18:27:21+00:00",
"lastTerminalAt": "2026-09-09T17:24:58.529069+00:00",
"lastTerminalAt": "2026-09-10T10:46:39.406893+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
@@ -4526,7 +4524,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 9,
"total": 10,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation": {
@@ -4678,19 +4676,19 @@
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm|text-generation": {
"attributableFailureCount": 8,
"consecutiveFailures": 8,
"attributableFailureCount": 7,
"consecutiveFailures": 7,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 8,
"decisionTotal": 7,
"failureBreakdown": {
"ambiguous_runtime": 12,
"framework_architecture_unsupported": 6,
"framework_architecture_unsupported": 5,
"model_load": 1,
"repository_structure": 1
},
"failureCount": 20,
"failureCount": 19,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -4702,7 +4700,7 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 20,
"total": 19,
"unresolvedFailureCount": 12
}
},
@@ -7053,13 +7051,13 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1557,
"totalRecords": 1644,
"terminalRecords": 1558,
"totalRecords": 1645,
"totals": {
"attributableFailureCount": 405,
"decisionFailureRate": 0.8882,
"decisionSuccessRate": 0.1118,
"decisionTotal": 456,
"attributableFailureCount": 406,
"decisionFailureRate": 0.8884,
"decisionSuccessRate": 0.1116,
"decisionTotal": 457,
"failureBreakdown": {
"ambiguous_runtime": 331,
"backend_operator": 34,
@@ -7069,25 +7067,25 @@
"platform_infrastructure": 2,
"repository_structure": 5,
"runtime_memory": 5,
"tokenizer_compatibility": 33,
"tokenizer_compatibility": 34,
"参数/模板问题": 95,
"验证失败": 673
},
"failureCount": 1506,
"failureRate": 0.9672,
"failureCount": 1507,
"failureRate": 0.9673,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 51,
"successRate": 0.0328,
"total": 1557,
"successRate": 0.0327,
"total": 1558,
"unresolvedFailureCount": 1099
},
"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 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。",
"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。",
@@ -7095,7 +7093,7 @@
"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 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。",
"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。",
@@ -7116,6 +7114,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1644,
"summarizedRecords": 1645,
"version": 1
}