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

state: generation 5131 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-10 11:08:22 +00:00
parent 21f87cd7c8
commit b9edcae2b5
9 changed files with 2048 additions and 2077 deletions
Download Patch File Download Diff File Expand all files Collapse all files

147
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-10T10:57:49.235436+00:00",
"lastSyncTime": "2026-09-10T10:57:49.001753+00:00",
"generatedAt": "2026-09-10T11:06:41.655720+00:00",
"lastSyncTime": "2026-09-10T11:06:41.315698+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -87,7 +87,7 @@
"ascend_910-b3|vllm|text-generation|model_type:qwen3_5_moe": {
"architectureSignature": "model_type:qwen3_5_moe",
"architectures": [],
"evidenceCount": 2,
"evidenceCount": 1,
"expiresAt": "2026-10-07T23:41:22+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-07T23:41:22+00:00",
@@ -95,12 +95,10 @@
"matchType": "model_type",
"modelType": "qwen3_5_moe",
"sourceModelIds": [
"mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B",
"mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B"
"mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B"
],
"sourceTaskIds": [
"4531788",
"4531835"
"4531788"
],
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation"
@@ -2048,27 +2046,27 @@
"unresolvedFailureCount": 33
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 30,
"attributableFailureCount": 32,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 30,
"decisionTotal": 32,
"failureBreakdown": {
"framework_architecture_unsupported": 2,
"platform_infrastructure": 1,
"tokenizer_compatibility": 28,
"platform_infrastructure": 2,
"tokenizer_compatibility": 30,
"参数/模板问题": 6
},
"failureCount": 37,
"failureCount": 40,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"platformFailureCount": 2,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 37,
"total": 40,
"unresolvedFailureCount": 6
},
"Sunrise_pt-200-x1|vllm|text-generation": {
@@ -2404,26 +2402,26 @@
"unresolvedFailureCount": 3
},
"vllm_fix_tokenizer": {
"attributableFailureCount": 33,
"attributableFailureCount": 35,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 33,
"decisionTotal": 35,
"failureBreakdown": {
"ambiguous_runtime": 29,
"framework_architecture_unsupported": 4,
"model_load": 1,
"platform_infrastructure": 1,
"tokenizer_compatibility": 28,
"platform_infrastructure": 2,
"tokenizer_compatibility": 30,
"参数/模板问题": 7
},
"failureCount": 70,
"failureCount": 73,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"platformFailureCount": 2,
"successCount": 0,
"successRate": 0.0,
"total": 70,
"total": 73,
"unresolvedFailureCount": 36
},
"vllm_tokenizer_patch": {
@@ -2445,7 +2443,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T10:57:49.230093+00:00",
"generatedAt": "2026-09-10T11:06:41.650381+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2702,25 +2700,25 @@
"unresolvedFailureCount": 60
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 31,
"decisionFailureRate": 0.9688,
"decisionSuccessRate": 0.0312,
"decisionTotal": 32,
"attributableFailureCount": 33,
"decisionFailureRate": 0.9706,
"decisionSuccessRate": 0.0294,
"decisionTotal": 34,
"failureBreakdown": {
"framework_architecture_unsupported": 3,
"platform_infrastructure": 2,
"tokenizer_compatibility": 28,
"platform_infrastructure": 3,
"tokenizer_compatibility": 30,
"参数/模板问题": 9,
"验证失败": 32
},
"failureCount": 74,
"failureRate": 0.9867,
"failureCount": 77,
"failureRate": 0.9872,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"platformFailureCount": 3,
"successCount": 1,
"successRate": 0.0133,
"total": 75,
"successRate": 0.0128,
"total": 78,
"unresolvedFailureCount": 41
},
"Vastai_va16": {
@@ -3985,17 +3983,17 @@
},
"recentCombinationStats": {
"Ascend_910-b3|vllm|text-generation": {
"attributableFailureCount": 3,
"consecutiveFailures": 3,
"attributableFailureCount": 2,
"consecutiveFailures": 2,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 3,
"decisionTotal": 2,
"failureBreakdown": {
"ambiguous_runtime": 17,
"framework_architecture_unsupported": 3
"framework_architecture_unsupported": 2
},
"failureCount": 20,
"failureCount": 19,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -4007,7 +4005,7 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 20,
"total": 19,
"unresolvedFailureCount": 17
},
"Ascend_910-b4|llamacpp|text-generation": {
@@ -4221,29 +4219,6 @@
"total": 2,
"unresolvedFailureCount": 2
},
"Iluvatar_bi-150|unknown|text-generation": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-07T22:14:22.623409+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 1.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm|text-generation": {
"attributableFailureCount": 4,
"consecutiveFailures": 4,
@@ -4476,30 +4451,30 @@
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 9,
"consecutiveFailures": 9,
"attributableFailureCount": 11,
"consecutiveFailures": 11,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 9,
"decisionTotal": 11,
"failureBreakdown": {
"framework_architecture_unsupported": 1,
"platform_infrastructure": 1,
"tokenizer_compatibility": 8
"platform_infrastructure": 2,
"tokenizer_compatibility": 10
},
"failureCount": 10,
"failureCount": 13,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": "2026-09-08T18:27:21+00:00",
"lastTerminalAt": "2026-09-10T10:46:39.406893+00:00",
"lastPlatformFailureAt": "2026-09-10T11:01:21+00:00",
"lastTerminalAt": "2026-09-10T11:06:41.315652+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"platformFailureCount": 2,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 10,
"total": 13,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation": {
@@ -7026,41 +7001,41 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1559,
"totalRecords": 1646,
"terminalRecords": 1562,
"totalRecords": 1649,
"totals": {
"attributableFailureCount": 406,
"decisionFailureRate": 0.8884,
"decisionSuccessRate": 0.1116,
"decisionTotal": 457,
"attributableFailureCount": 408,
"decisionFailureRate": 0.8889,
"decisionSuccessRate": 0.1111,
"decisionTotal": 459,
"failureBreakdown": {
"ambiguous_runtime": 332,
"backend_operator": 34,
"framework_architecture_unsupported": 271,
"memory_capacity": 11,
"model_load": 46,
"platform_infrastructure": 2,
"platform_infrastructure": 3,
"repository_structure": 5,
"runtime_memory": 5,
"tokenizer_compatibility": 34,
"tokenizer_compatibility": 36,
"参数/模板问题": 95,
"验证失败": 673
},
"failureCount": 1508,
"failureCount": 1511,
"failureRate": 0.9673,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"platformFailureCount": 3,
"successCount": 51,
"successRate": 0.0327,
"total": 1559,
"total": 1562,
"unresolvedFailureCount": 1100
},
"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。",
@@ -7068,7 +7043,7 @@
"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。",
@@ -7089,6 +7064,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1646,
"summarizedRecords": 1649,
"version": 1
}