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

state: generation 5332 (intent)

Browse Source
This commit is contained in:
CoolBoy
2026-09-10 19:50:30 +00:00
parent 2303f48519
commit 1018664029
7 changed files with 1408 additions and 1311 deletions
Download Patch File Download Diff File Expand all files Collapse all files

96
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-10T19:38:05.803026+00:00",
"lastSyncTime": "2026-09-10T19:38:05.602511+00:00",
"generatedAt": "2026-09-10T19:48:10.294794+00:00",
"lastSyncTime": "2026-09-10T19:48:09.995356+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -401,7 +401,7 @@
"cambricon_mlu-370-x8|vllm-mlu|text-generation|model_type:qwen3_5_mtp": {
"architectureSignature": "model_type:qwen3_5_mtp",
"architectures": [],
"evidenceCount": 2,
"evidenceCount": 1,
"expiresAt": "2026-10-08T06:46:11.587867+00:00",
"framework": "vllm-mlu",
"latestFailureAt": "2026-09-08T06:46:11.587867+00:00",
@@ -409,12 +409,10 @@
"matchType": "model_type",
"modelType": "qwen3_5_mtp",
"sourceModelIds": [
"mlx-community/Qwen3.8-27B-MTP-nvfp4",
"mlx-community/Qwen3.8-27B-MTP-mxfp4"
"mlx-community/Qwen3.8-27B-MTP-nvfp4"
],
"sourceTaskIds": [
"4712816",
"4712822"
"4712816"
],
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation"
@@ -2144,12 +2142,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 44,
"failureBreakdown": {
"ambiguous_runtime": 57,
"ambiguous_runtime": 58,
"framework_architecture_unsupported": 38,
"memory_capacity": 1,
"model_load": 5
},
"failureCount": 101,
"failureCount": 102,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2159,8 +2157,8 @@
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 101,
"unresolvedFailureCount": 57
"total": 102,
"unresolvedFailureCount": 58
},
"hygon_k100-ai|llamacpp|text-generation": {
"attributableFailureCount": 0,
@@ -2323,7 +2321,7 @@
"decisionSuccessRate": 0.0083,
"decisionTotal": 242,
"failureBreakdown": {
"ambiguous_runtime": 184,
"ambiguous_runtime": 185,
"backend_operator": 33,
"framework_architecture_unsupported": 169,
"memory_capacity": 6,
@@ -2334,15 +2332,15 @@
"tokenizer_compatibility": 3,
"参数/模板问题": 24
},
"failureCount": 449,
"failureCount": 450,
"failureRate": 0.9956,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 2,
"successRate": 0.0044,
"total": 451,
"unresolvedFailureCount": 208
"total": 452,
"unresolvedFailureCount": 209
},
"vllm-mlu": {
"attributableFailureCount": 7,
@@ -2445,7 +2443,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T19:38:05.798763+00:00",
"generatedAt": "2026-09-10T19:48:10.290792+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2731,22 +2729,22 @@
"decisionSuccessRate": 0.2167,
"decisionTotal": 60,
"failureBreakdown": {
"ambiguous_runtime": 59,
"ambiguous_runtime": 60,
"framework_architecture_unsupported": 40,
"memory_capacity": 1,
"model_load": 6,
"参数/模板问题": 13,
"验证失败": 130
},
"failureCount": 249,
"failureRate": 0.9504,
"failureCount": 250,
"failureRate": 0.9506,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 13,
"successRate": 0.0496,
"total": 262,
"unresolvedFailureCount": 202
"successRate": 0.0494,
"total": 263,
"unresolvedFailureCount": 203
},
"hygon_k100-ai": {
"attributableFailureCount": 39,
@@ -4165,18 +4163,18 @@
"unresolvedFailureCount": 14
},
"Cambricon_mlu-370-x8|vllm-mlu|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": 3,
"framework_architecture_unsupported": 3,
"framework_architecture_unsupported": 2,
"参数/模板问题": 1
},
"failureCount": 7,
"failureCount": 6,
"failureRate": 1.0,
"framework": "vllm-mlu",
"lastPlatformFailureAt": null,
@@ -4188,7 +4186,7 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 7,
"total": 6,
"unresolvedFailureCount": 4
},
"Cambricon_mlu-370-x8|vllm|text-generation": {
@@ -4541,7 +4539,7 @@
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T16:05:31.804365+00:00",
"lastTerminalAt": "2026-09-10T19:48:09.995356+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4659,15 +4657,15 @@
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3_5_mtp|none": {
"attributableFailureCount": 2,
"consecutiveFailures": 2,
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 2
"framework_architecture_unsupported": 1
},
"failureCount": 2,
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"lastTerminalAt": "2026-09-08T18:40:55.416623+00:00",
@@ -4680,7 +4678,7 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 2,
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm|text-generation|qwen3_5_moe|eschamoe": {
@@ -7022,15 +7020,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1627,
"totalRecords": 1714,
"terminalRecords": 1628,
"totalRecords": 1715,
"totals": {
"attributableFailureCount": 425,
"decisionFailureRate": 0.891,
"decisionSuccessRate": 0.109,
"decisionTotal": 477,
"failureBreakdown": {
"ambiguous_runtime": 375,
"ambiguous_runtime": 376,
"backend_operator": 40,
"framework_architecture_unsupported": 273,
"memory_capacity": 11,
@@ -7042,30 +7040,31 @@
"参数/模板问题": 98,
"验证失败": 673
},
"failureCount": 1575,
"failureRate": 0.968,
"failureCount": 1576,
"failureRate": 0.9681,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 52,
"successRate": 0.032,
"total": 1627,
"unresolvedFailureCount": 1146
"successRate": 0.0319,
"total": 1628,
"unresolvedFailureCount": 1147
},
"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 Iluvatar_bi-150 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 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 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。",
"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。",
@@ -7080,11 +7079,10 @@
"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": 1714,
"summarizedRecords": 1715,
"version": 1
}