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

state: generation 11488 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-21 14:04:21 +00:00
parent 6742846af1
commit 0e142bf0ee
11 changed files with 2177 additions and 2001 deletions
Download Patch File Download Diff File Expand all files Collapse all files

290
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-21T13:30:37.394010+00:00",
"lastSyncTime": "2026-09-21T13:30:37.066051+00:00",
"generatedAt": "2026-09-21T14:04:19.981384+00:00",
"lastSyncTime": "2026-09-21T14:04:19.915587+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1760,6 +1760,25 @@
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation"
},
"kunlunxin_p-800|vllm_tokenizer_patch|text-generation|model_type:muse_glimmer": {
"architectureSignature": "model_type:muse_glimmer",
"architectures": [],
"evidenceCount": 1,
"expiresAt": "2026-10-20T03:46:29.643802+00:00",
"framework": "vllm_tokenizer_patch",
"latestFailureAt": "2026-09-20T03:46:29.643802+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "muse_glimmer",
"sourceModelIds": [
"ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit"
],
"sourceTaskIds": [
"4970111"
],
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation"
},
"kunlunxin_p-800|vllm_tokenizer_patch|text-generation|model_type:nemotron_h": {
"architectureSignature": "model_type:nemotron_h",
"architectures": [],
@@ -2674,7 +2693,7 @@
}
},
"architectureCompatibilitySummary": {
"activeBlockCount": 134,
"activeBlockCount": 135,
"byGpuFramework": {
"Ascend_910-b3|vllm": 13,
"Ascend_910-b3|vllm_tokenizer_patch": 5,
@@ -2689,7 +2708,7 @@
"Iluvatar_bi-150|vllm": 7,
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 3,
"Kunlunxin_p-800|vllm": 1,
"Kunlunxin_p-800|vllm_tokenizer_patch": 5,
"Kunlunxin_p-800|vllm_tokenizer_patch": 6,
"MetaX_c-500|vllm": 7,
"Mthreads_s4000|vllm": 9,
"Sunrise_pt-200-x1|vllm": 3,
@@ -4300,10 +4319,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 98,
"ambiguous_runtime": 100,
"参数/模板问题": 3
},
"failureCount": 101,
"failureCount": 103,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -4313,21 +4332,21 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 101,
"unresolvedFailureCount": 101
"total": 103,
"unresolvedFailureCount": 103
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 14,
"attributableFailureCount": 15,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 14,
"decisionTotal": 15,
"failureBreakdown": {
"ambiguous_runtime": 1,
"backend_operator": 1,
"framework_architecture_unsupported": 13,
"framework_architecture_unsupported": 14,
"参数/模板问题": 12
},
"failureCount": 27,
"failureCount": 28,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"pendingCount": 0,
@@ -4337,7 +4356,7 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 27,
"total": 28,
"unresolvedFailureCount": 13
},
"Kunlunxin_p-800|vllm|text-generation": {
@@ -5445,7 +5464,7 @@
"decisionSuccessRate": 0.0391,
"decisionTotal": 128,
"failureBreakdown": {
"ambiguous_runtime": 166,
"ambiguous_runtime": 168,
"backend_operator": 8,
"framework_architecture_unsupported": 23,
"memory_capacity": 7,
@@ -5454,26 +5473,26 @@
"tokenizer_compatibility": 82,
"参数/模板问题": 13
},
"failureCount": 319,
"failureRate": 0.9846,
"failureCount": 321,
"failureRate": 0.9847,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 17,
"successCount": 5,
"successRate": 0.0154,
"total": 324,
"unresolvedFailureCount": 179
"successRate": 0.0153,
"total": 326,
"unresolvedFailureCount": 181
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 68,
"decisionFailureRate": 0.9714,
"decisionSuccessRate": 0.0286,
"decisionTotal": 70,
"attributableFailureCount": 69,
"decisionFailureRate": 0.9718,
"decisionSuccessRate": 0.0282,
"decisionTotal": 71,
"failureBreakdown": {
"ambiguous_runtime": 61,
"backend_operator": 1,
"context_length": 2,
"framework_architecture_unsupported": 60,
"framework_architecture_unsupported": 61,
"memory_capacity": 1,
"model_load": 2,
"platform_infrastructure": 1,
@@ -5481,18 +5500,18 @@
"tokenizer_compatibility": 1,
"参数/模板问题": 26
},
"failureCount": 156,
"failureRate": 0.9873,
"failureCount": 157,
"failureRate": 0.9874,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 2,
"successRate": 0.0127,
"total": 158,
"successRate": 0.0126,
"total": 159,
"unresolvedFailureCount": 87
}
},
"generatedAt": "2026-09-21T13:30:37.383788+00:00",
"generatedAt": "2026-09-21T14:04:19.970747+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 94,
@@ -5717,28 +5736,28 @@
"unresolvedFailureCount": 716
},
"Kunlunxin_p-800": {
"attributableFailureCount": 16,
"attributableFailureCount": 17,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 16,
"decisionTotal": 17,
"failureBreakdown": {
"ambiguous_runtime": 174,
"ambiguous_runtime": 176,
"backend_operator": 1,
"framework_architecture_unsupported": 14,
"framework_architecture_unsupported": 15,
"memory_capacity": 1,
"参数/模板问题": 19,
"日志缺失": 1,
"验证失败": 23
},
"failureCount": 233,
"failureCount": 236,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 233,
"unresolvedFailureCount": 217
"total": 236,
"unresolvedFailureCount": 219
},
"Kunlunxin_r-200-8f": {
"attributableFailureCount": 0,
@@ -5924,7 +5943,7 @@
"hygon_k100-ai": 64.0
},
"pendingRecords": 0,
"policyCancelledRecords": 184,
"policyCancelledRecords": 185,
"profileCombinationStats": {
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|bailing_hybrid|none": {
"attributableFailureCount": 1,
@@ -12853,6 +12872,29 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|lfm2_moe|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "lfm2_moe",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|llama|awq": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -12951,9 +12993,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "muse_glimmer",
@@ -12965,8 +13007,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|nemotron_h|none": {
"attributableFailureCount": 0,
@@ -13521,6 +13563,29 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|muse_glimmer|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "muse_glimmer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|nemotron_h|compressed-tensors": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -16602,13 +16667,13 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 4
"ambiguous_runtime": 5
},
"failureCount": 4,
"failureCount": 5,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-21T08:44:09.587569+00:00",
"lastTerminalAt": "2026-09-21T13:58:33.470387+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -16616,8 +16681,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 4,
"unresolvedFailureCount": 4
"total": 5,
"unresolvedFailureCount": 5
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 2,
@@ -16629,13 +16694,13 @@
"failureBreakdown": {
"backend_operator": 1,
"framework_architecture_unsupported": 1,
"参数/模板问题": 4
"参数/模板问题": 3
},
"failureCount": 6,
"failureCount": 5,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-21T02:15:17.867324+00:00",
"lastTerminalAt": "2026-09-21T13:58:33.470413+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -16643,8 +16708,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 6,
"unresolvedFailureCount": 4
"total": 5,
"unresolvedFailureCount": 3
},
"MetaX_c-500|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -19913,6 +19978,31 @@
"total": 2,
"unresolvedFailureCount": 2
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|lfm2_moe|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastTerminalAt": "2026-09-21T13:58:33.470387+00:00",
"modelType": "lfm2_moe",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|llama|compressed-tensors": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -19988,7 +20078,7 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|spark2_5|none": {
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|muse_glimmer|none": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"decisionFailureRate": 1.0,
@@ -20000,8 +20090,8 @@
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastTerminalAt": "2026-09-21T08:25:31.485651+00:00",
"modelType": "spark2_5",
"lastTerminalAt": "2026-09-21T13:58:33.470413+00:00",
"modelType": "muse_glimmer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -29970,6 +30060,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|lfm2_moe|none|33": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 33,
"modelType": "lfm2_moe",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|llama|awq|30": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -30234,6 +30348,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|muse_glimmer|none|35": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 35,
"modelType": "muse_glimmer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|nemotron_h|none|34": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -31195,6 +31333,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|muse_glimmer|none|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 34,
"modelType": "muse_glimmer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|nemotron_h|compressed-tensors|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -34881,20 +35043,20 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 16280,
"totalRecords": 16464,
"terminalRecords": 16283,
"totalRecords": 16468,
"totals": {
"attributableFailureCount": 5881,
"attributableFailureCount": 5882,
"decisionFailureRate": 0.8617,
"decisionSuccessRate": 0.1383,
"decisionTotal": 6825,
"decisionTotal": 6826,
"failureBreakdown": {
"ambiguous_runtime": 3949,
"ambiguous_runtime": 3951,
"architecture_compatibility": 212,
"attention_backend": 1,
"backend_operator": 103,
"context_length": 320,
"framework_architecture_unsupported": 2069,
"framework_architecture_unsupported": 2070,
"memory_capacity": 1197,
"model_load": 498,
"platform_infrastructure": 925,
@@ -34905,15 +35067,15 @@
"日志缺失": 719,
"验证失败": 674
},
"failureCount": 15336,
"failureCount": 15339,
"failureRate": 0.942,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 925,
"successCount": 944,
"successRate": 0.058,
"total": 16280,
"unresolvedFailureCount": 8530
"total": 16283,
"unresolvedFailureCount": 8532
},
"warnings": [
"GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -34969,6 +35131,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 16464,
"summarizedRecords": 16468,
"version": 1
}