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

state: generation 18833 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-30 15:31:23 +00:00
parent 11076ab73a
commit 9f00a53dcd
9 changed files with 1730 additions and 1660 deletions
Download Patch File Download Diff File Expand all files Collapse all files

292
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-30T15:20:12.430635+00:00",
"lastSyncTime": "2026-09-30T15:20:12.157904+00:00",
"generatedAt": "2026-09-30T15:29:22.929866+00:00",
"lastSyncTime": "2026-09-30T15:29:22.559055+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -3443,30 +3443,30 @@
"unresolvedFailureCount": 1
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 38,
"decisionFailureRate": 0.9048,
"decisionSuccessRate": 0.0952,
"decisionTotal": 42,
"attributableFailureCount": 39,
"decisionFailureRate": 0.907,
"decisionSuccessRate": 0.093,
"decisionTotal": 43,
"failureBreakdown": {
"ambiguous_runtime": 70,
"context_length": 7,
"ambiguous_runtime": 73,
"context_length": 8,
"framework_architecture_unsupported": 30,
"memory_capacity": 1,
"platform_infrastructure": 1,
"参数/模板问题": 8
},
"failureCount": 117,
"failureRate": 0.9669,
"failureCount": 121,
"failureRate": 0.968,
"framework": "vllm_tokenizer_patch",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 4,
"successRate": 0.0331,
"successRate": 0.032,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 121,
"unresolvedFailureCount": 78
"total": 125,
"unresolvedFailureCount": 81
},
"Ascend_910-b3|vllm|text-generation": {
"attributableFailureCount": 69,
@@ -6168,14 +6168,14 @@
"unresolvedFailureCount": 347
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 136,
"decisionFailureRate": 0.9315,
"decisionSuccessRate": 0.0685,
"decisionTotal": 146,
"attributableFailureCount": 137,
"decisionFailureRate": 0.932,
"decisionSuccessRate": 0.068,
"decisionTotal": 147,
"failureBreakdown": {
"ambiguous_runtime": 182,
"ambiguous_runtime": 185,
"backend_operator": 15,
"context_length": 7,
"context_length": 8,
"framework_architecture_unsupported": 81,
"memory_capacity": 2,
"model_load": 23,
@@ -6185,27 +6185,27 @@
"tokenizer_compatibility": 2,
"参数/模板问题": 29
},
"failureCount": 350,
"failureRate": 0.9722,
"failureCount": 354,
"failureRate": 0.9725,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 3,
"successCount": 10,
"successRate": 0.0278,
"total": 360,
"unresolvedFailureCount": 211
"successRate": 0.0275,
"total": 364,
"unresolvedFailureCount": 214
}
},
"generatedAt": "2026-09-30T15:20:12.415440+00:00",
"generatedAt": "2026-09-30T15:29:22.917040+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 108,
"decisionFailureRate": 0.8308,
"decisionSuccessRate": 0.1692,
"decisionTotal": 130,
"attributableFailureCount": 109,
"decisionFailureRate": 0.8321,
"decisionSuccessRate": 0.1679,
"decisionTotal": 131,
"failureBreakdown": {
"ambiguous_runtime": 138,
"context_length": 7,
"ambiguous_runtime": 141,
"context_length": 8,
"framework_architecture_unsupported": 95,
"memory_capacity": 2,
"platform_infrastructure": 1,
@@ -6215,15 +6215,15 @@
"日志缺失": 3,
"验证失败": 27
},
"failureCount": 316,
"failureRate": 0.9349,
"failureCount": 320,
"failureRate": 0.9357,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 22,
"successRate": 0.0651,
"total": 338,
"unresolvedFailureCount": 207
"successRate": 0.0643,
"total": 342,
"unresolvedFailureCount": 210
},
"Ascend_910-b4": {
"attributableFailureCount": 325,
@@ -6710,9 +6710,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 9
"ambiguous_runtime": 10
},
"failureCount": 9,
"failureCount": 10,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "gemma2",
@@ -6724,8 +6724,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 9,
"unresolvedFailureCount": 9
"total": 10,
"unresolvedFailureCount": 10
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|gemma3|compressed-tensors": {
"attributableFailureCount": 0,
@@ -6889,15 +6889,15 @@
"unresolvedFailureCount": 6
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|compressed-tensors": {
"attributableFailureCount": 5,
"attributableFailureCount": 6,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 5,
"decisionTotal": 6,
"failureBreakdown": {
"ambiguous_runtime": 12,
"context_length": 5
"ambiguous_runtime": 13,
"context_length": 6
},
"failureCount": 17,
"failureCount": 19,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "llama",
@@ -6909,8 +6909,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 17,
"unresolvedFailureCount": 12
"total": 19,
"unresolvedFailureCount": 13
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|none": {
"attributableFailureCount": 0,
@@ -6964,9 +6964,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "mistral",
@@ -6978,8 +6978,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|mpt|none": {
"attributableFailureCount": 2,
@@ -23614,22 +23614,22 @@
"unresolvedFailureCount": 12
},
"Ascend_910-b3|vllm_tokenizer_patch|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": 4,
"context_length": 1,
"ambiguous_runtime": 7,
"context_length": 2,
"framework_architecture_unsupported": 1
},
"failureCount": 6,
"failureCount": 10,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-30T11:45:44.243364+00:00",
"lastTerminalAt": "2026-09-30T15:29:22.559035+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -23637,8 +23637,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 6,
"unresolvedFailureCount": 4
"total": 10,
"unresolvedFailureCount": 7
},
"Ascend_910-b3|vllm|text-generation": {
"attributableFailureCount": 2,
@@ -23724,10 +23724,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 7,
"ambiguous_runtime": 5,
"platform_infrastructure": 1
},
"failureCount": 8,
"failureCount": 6,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": "2026-09-21T09:13:58.610056+00:00",
@@ -23739,8 +23739,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 8,
"unresolvedFailureCount": 7
"total": 6,
"unresolvedFailureCount": 5
},
"Biren_166m|unknown|text-generation": {
"attributableFailureCount": 2,
@@ -24271,7 +24271,7 @@
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 6,
"decisionTotal": 5,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
@@ -24281,11 +24281,11 @@
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 6,
"successCount": 5,
"successRate": 1.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 6,
"total": 5,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
@@ -24421,20 +24421,45 @@
}
},
"recentProfileCombinationStats": {
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|compressed-tensors": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"decisionFailureRate": 1.0,
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|gemma2|compressed-tensors": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2,
"context_length": 1
"ambiguous_runtime": 1
},
"failureCount": 3,
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastTerminalAt": "2026-09-30T11:45:44.243364+00:00",
"lastTerminalAt": "2026-09-30T15:29:22.559055+00:00",
"modelType": "gemma2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|compressed-tensors": {
"attributableFailureCount": 2,
"consecutiveFailures": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"failureBreakdown": {
"ambiguous_runtime": 3,
"context_length": 2
},
"failureCount": 5,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastTerminalAt": "2026-09-30T15:29:22.559035+00:00",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
@@ -24444,8 +24469,33 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 3,
"unresolvedFailureCount": 2
"total": 5,
"unresolvedFailureCount": 3
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|mistral|compressed-tensors": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastTerminalAt": "2026-09-30T15:29:22.559006+00:00",
"modelType": "mistral",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|phi3small|compressed-tensors": {
"attributableFailureCount": 1,
@@ -27222,15 +27272,15 @@
"unresolvedFailureCount": 0
},
"Kunlunxin_p-800|vllm|text-generation|starcoder2|compressed-tensors": {
"attributableFailureCount": 4,
"consecutiveFailures": 4,
"attributableFailureCount": 3,
"consecutiveFailures": 3,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 4,
"decisionTotal": 3,
"failureBreakdown": {
"backend_operator": 4
"backend_operator": 3
},
"failureCount": 4,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm",
"lastTerminalAt": "2026-09-23T02:35:34.755698+00:00",
@@ -27243,7 +27293,7 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 4,
"total": 3,
"unresolvedFailureCount": 0
},
"Kunlunxin_p-800|vllm|text-generation|zaya|none": {
@@ -27623,9 +27673,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 6
"ambiguous_runtime": 7
},
"failureCount": 6,
"failureCount": 7,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 32,
@@ -27638,8 +27688,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 6,
"unresolvedFailureCount": 6
"total": 7,
"unresolvedFailureCount": 7
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|gemma2|compressed-tensors|33": {
"attributableFailureCount": 0,
@@ -28026,15 +28076,15 @@
"unresolvedFailureCount": 0
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|compressed-tensors|30": {
"attributableFailureCount": 1,
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {
"ambiguous_runtime": 2,
"context_length": 1
"context_length": 2
},
"failureCount": 3,
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 30,
@@ -28047,7 +28097,7 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 3,
"total": 4,
"unresolvedFailureCount": 2
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|compressed-tensors|32": {
@@ -28080,9 +28130,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 7
"ambiguous_runtime": 8
},
"failureCount": 7,
"failureCount": 8,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 33,
@@ -28095,8 +28145,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 7,
"unresolvedFailureCount": 7
"total": 8,
"unresolvedFailureCount": 8
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|compressed-tensors|35": {
"attributableFailureCount": 0,
@@ -28218,6 +28268,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|mistral|compressed-tensors|33": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 33,
"modelType": "mistral",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|mpt|none|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -53645,19 +53719,19 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17158,
"totalRecords": 17379,
"terminalRecords": 17162,
"totalRecords": 17383,
"totals": {
"attributableFailureCount": 6150,
"attributableFailureCount": 6151,
"decisionFailureRate": 0.8632,
"decisionSuccessRate": 0.1368,
"decisionTotal": 7125,
"decisionTotal": 7126,
"failureBreakdown": {
"ambiguous_runtime": 4467,
"ambiguous_runtime": 4470,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 128,
"context_length": 325,
"context_length": 326,
"framework_architecture_unsupported": 2198,
"memory_capacity": 1206,
"model_load": 550,
@@ -53669,30 +53743,30 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16183,
"failureCount": 16187,
"failureRate": 0.9432,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 943,
"successCount": 975,
"successRate": 0.0568,
"total": 17158,
"unresolvedFailureCount": 9090
"total": 17162,
"unresolvedFailureCount": 9093
},
"warnings": [
"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 Biren_166m 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 Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Iluvatar_bi-100 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-x8 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 Kunlunxin_p-800 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 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。",
"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。",
"GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
"组合 Ascend_910-b4|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Kunlunxin_p-800|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -53737,6 +53811,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17379,
"summarizedRecords": 17383,
"version": 1
}