state: generation 6467 (cycle)

.modelhub_state/architecture_compatibility_blacklist.json

@@ -1452,7 +1452,7 @@
       "taskType": "text-generation"
     }
   },
-  "generatedAt": "2026-09-13T02:02:42.919741+00:00",
+  "generatedAt": "2026-09-13T02:05:24.702858+00:00",
   "summary": {
     "activeBlockCount": 73,
     "byGpuFramework": {

.modelhub_state/architecture_history_backfill.json

@@ -27,7 +27,7 @@
     "11": {
       "complete": false,
       "lastError": "ModelHubAPIError: 系统错误",
-      "listingErrors": 467,
+      "listingErrors": 468,
       "nextPage": 1,
       "recordsScanned": 0,
       "uniqueRecords": 0
@@ -102,12 +102,12 @@
   "cutoffAt": "2026-09-04T03:55:51.365685+00:00",
   "failureLogsInspected": 0,
   "mode": "incremental_decision_only",
-  "nextAccountIndex": 11,
+  "nextAccountIndex": 0,
   "recordsScanned": 0,
   "seenTaskIds": [],
   "startedAt": "2026-09-04T03:55:51.365685+00:00",
   "terminalRecords": 0,
   "uniqueRecords": 0,
-  "updatedAt": "2026-09-13T02:02:42.896746+00:00",
+  "updatedAt": "2026-09-13T02:05:24.672409+00:00",
   "version": 1
 }

.modelhub_state/market_intelligence.json

@@ -416,7 +416,7 @@
     }
   },
   "frameworkUpdatedAt": null,
-  "generatedAt": "2026-09-13T02:01:01.844629+00:00",
+  "generatedAt": "2026-09-13T02:03:50.767216+00:00",
   "gpuStats": {
     "Ascend_910-b3": {
       "available": true,

.modelhub_state/outcome_checkpoint.json

@@ -1,6 +1,6 @@
 {
-  "generatedAt": "2026-09-13T01:11:40.476006+00:00",
+  "generatedAt": "2026-09-13T02:03:44.065901+00:00",
-  "lastSyncTime": "2026-09-13T01:11:40.231412+00:00",
+  "lastSyncTime": "2026-09-13T02:03:43.839608+00:00",
   "recentLimit": 300,
   "report": {
     "architectureCompatibilityBlocks": {
@@ -2070,30 +2070,30 @@
         "unresolvedFailureCount": 56
       },
       "MetaX_c-500|vllm|text-generation": {
-        "attributableFailureCount": 52,
+        "attributableFailureCount": 53,
-        "decisionFailureRate": 0.9455,
+        "decisionFailureRate": 0.9464,
-        "decisionSuccessRate": 0.0545,
+        "decisionSuccessRate": 0.0536,
-        "decisionTotal": 55,
+        "decisionTotal": 56,
         "failureBreakdown": {
           "ambiguous_runtime": 9,
           "backend_operator": 27,
-          "framework_architecture_unsupported": 16,
+          "framework_architecture_unsupported": 17,
           "memory_capacity": 1,
           "model_load": 7,
           "repository_structure": 1,
           "参数/模板问题": 9
         },
-        "failureCount": 70,
+        "failureCount": 71,
-        "failureRate": 0.9589,
+        "failureRate": 0.9595,
         "framework": "vllm",
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 0,
         "successCount": 3,
-        "successRate": 0.0411,
+        "successRate": 0.0405,
         "targetGpu": "MetaX_c-500",
         "taskType": "text-generation",
-        "total": 73,
+        "total": 74,
         "unresolvedFailureCount": 18
       },
       "Mthreads_s4000|llamacpp|text-generation": {
@@ -2486,14 +2486,14 @@
         "unresolvedFailureCount": 870
       },
       "vllm": {
-        "attributableFailureCount": 285,
+        "attributableFailureCount": 286,
         "decisionFailureRate": 0.9896,
         "decisionSuccessRate": 0.0104,
-        "decisionTotal": 288,
+        "decisionTotal": 289,
         "failureBreakdown": {
           "ambiguous_runtime": 201,
           "backend_operator": 34,
-          "framework_architecture_unsupported": 199,
+          "framework_architecture_unsupported": 200,
           "memory_capacity": 6,
           "model_load": 26,
           "platform_infrastructure": 1,
@@ -2502,14 +2502,14 @@
           "tokenizer_compatibility": 6,
           "参数/模板问题": 24
         },
-        "failureCount": 511,
+        "failureCount": 512,
         "failureRate": 0.9942,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 1,
         "successCount": 3,
         "successRate": 0.0058,
-        "total": 514,
+        "total": 515,
         "unresolvedFailureCount": 225
       },
       "vllm-mlu": {
@@ -2614,7 +2614,7 @@
         "unresolvedFailureCount": 1
       }
     },
-    "generatedAt": "2026-09-13T01:11:40.471500+00:00",
+    "generatedAt": "2026-09-13T02:03:44.061319+00:00",
     "gpuSummaries": {
       "Ascend_910-b3": {
         "attributableFailureCount": 30,
@@ -2823,28 +2823,28 @@
         "unresolvedFailureCount": 94
       },
       "MetaX_c-500": {
-        "attributableFailureCount": 52,
+        "attributableFailureCount": 53,
-        "decisionFailureRate": 0.8125,
+        "decisionFailureRate": 0.8154,
-        "decisionSuccessRate": 0.1875,
+        "decisionSuccessRate": 0.1846,
-        "decisionTotal": 64,
+        "decisionTotal": 65,
         "failureBreakdown": {
           "ambiguous_runtime": 9,
           "backend_operator": 27,
-          "framework_architecture_unsupported": 16,
+          "framework_architecture_unsupported": 17,
           "memory_capacity": 1,
           "model_load": 7,
           "repository_structure": 1,
           "参数/模板问题": 17,
           "验证失败": 48
         },
-        "failureCount": 126,
+        "failureCount": 127,
-        "failureRate": 0.913,
+        "failureRate": 0.9137,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 0,
         "successCount": 12,
-        "successRate": 0.087,
+        "successRate": 0.0863,
-        "total": 138,
+        "total": 139,
         "unresolvedFailureCount": 74
       },
       "Mthreads_s4000": {
@@ -3972,6 +3972,29 @@
         "total": 2,
         "unresolvedFailureCount": 0
       },
+      "MetaX_c-500|vllm|text-generation|spark2_5|none": {
+        "attributableFailureCount": 1,
+        "decisionFailureRate": 1.0,
+        "decisionSuccessRate": 0.0,
+        "decisionTotal": 1,
+        "failureBreakdown": {
+          "framework_architecture_unsupported": 1
+        },
+        "failureCount": 1,
+        "failureRate": 1.0,
+        "framework": "vllm",
+        "modelType": "spark2_5",
+        "pendingCount": 0,
+        "pendingRate": 0.0,
+        "platformFailureCount": 0,
+        "quantizationMethod": "none",
+        "successCount": 0,
+        "successRate": 0.0,
+        "targetGpu": "MetaX_c-500",
+        "taskType": "text-generation",
+        "total": 1,
+        "unresolvedFailureCount": 0
+      },
       "MetaX_c-500|vllm|text-generation|starcoder2|compressed-tensors": {
         "attributableFailureCount": 7,
         "decisionFailureRate": 0.875,
@@ -6765,6 +6788,30 @@
         "total": 1,
         "unresolvedFailureCount": 0
       },
+      "MetaX_c-500|vllm|text-generation|spark2_5|none|32": {
+        "attributableFailureCount": 1,
+        "decisionFailureRate": 1.0,
+        "decisionSuccessRate": 0.0,
+        "decisionTotal": 1,
+        "failureBreakdown": {
+          "framework_architecture_unsupported": 1
+        },
+        "failureCount": 1,
+        "failureRate": 1.0,
+        "framework": "vllm",
+        "loadSizeLog2Bucket": 32,
+        "modelType": "spark2_5",
+        "pendingCount": 0,
+        "pendingRate": 0.0,
+        "platformFailureCount": 0,
+        "quantizationMethod": "none",
+        "successCount": 0,
+        "successRate": 0.0,
+        "targetGpu": "MetaX_c-500",
+        "taskType": "text-generation",
+        "total": 1,
+        "unresolvedFailureCount": 0
+      },
       "MetaX_c-500|vllm|text-generation|starcoder2|compressed-tensors|31": {
         "attributableFailureCount": 2,
         "decisionFailureRate": 1.0,
@@ -7294,17 +7341,17 @@
         "unresolvedFailureCount": 0
       }
     },
-    "terminalRecords": 1747,
+    "terminalRecords": 1748,
-    "totalRecords": 1834,
+    "totalRecords": 1835,
     "totals": {
-      "attributableFailureCount": 500,
+      "attributableFailureCount": 501,
-      "decisionFailureRate": 0.8961,
+      "decisionFailureRate": 0.8962,
-      "decisionSuccessRate": 0.1039,
+      "decisionSuccessRate": 0.1038,
-      "decisionTotal": 558,
+      "decisionTotal": 559,
       "failureBreakdown": {
         "ambiguous_runtime": 411,
         "backend_operator": 42,
-        "framework_architecture_unsupported": 312,
+        "framework_architecture_unsupported": 313,
         "memory_capacity": 11,
         "model_load": 73,
         "platform_infrastructure": 4,
@@ -7314,20 +7361,21 @@
         "参数/模板问题": 101,
         "验证失败": 673
       },
-      "failureCount": 1689,
+      "failureCount": 1690,
       "failureRate": 0.9668,
       "pendingCount": 0,
       "pendingRate": 0.0,
       "platformFailureCount": 4,
       "successCount": 58,
       "successRate": 0.0332,
-      "total": 1747,
+      "total": 1748,
       "unresolvedFailureCount": 1185
     },
     "warnings": [
       "GPU Ascend_910-b3 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 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 Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -7336,7 +7384,6 @@
       "GPU MetaX_c-500 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 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。",
       "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。",
       "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 Ascend_910-b4|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -7359,6 +7406,6 @@
     ]
   },
   "storageMode": "decision_state_only",
-  "summarizedRecords": 1834,
+  "summarizedRecords": 1835,
   "version": 1
 }

manifest.json

@@ -1,24 +1,24 @@
 {
   "agentVersion": "2026.09.04.4",
   "checksums": {
-    ".modelhub_state/architecture_compatibility_blacklist.json": "ade5c61e12824ac0599607d3a46a36ddafa9b20c9840a7b5227ec024637543d3",
+    ".modelhub_state/architecture_compatibility_blacklist.json": "922b99abc055034af2e4dd7f9b694497c842bbede9ae8b359a7f24ad180ab77c",
-    ".modelhub_state/architecture_history_backfill.json": "71bb1f32d4eadd95d1f5174035e0b594e850e490afeb3795c90652d31c2a92d6",
+    ".modelhub_state/architecture_history_backfill.json": "b7926ef5dde60dbfdbdf8927090b66c2eca123fae0e12d318ce9b68885a2d75a",
-    ".modelhub_state/market_intelligence.json": "068e61012be507dfe1caaaf5a4264583497abd41e25c1e5ebfbfcc12b11a7087",
+    ".modelhub_state/market_intelligence.json": "f7cb172be94d29266901976412d85bef36cfaf3051b07014c74337e641e20ee3",
-    ".modelhub_state/official_capabilities.json": "c8f520ecbc3498e3c7c8339c4bc2724dde94b63a4a9c9349d111efd58496d745",
+    ".modelhub_state/official_capabilities.json": "e25295cc709cfdef1a014806903d94f465bf99ae888b117df0b10e8ec8c0dde3",
-    ".modelhub_state/outcome_checkpoint.json": "ab941da324bf814b6fe065e115cc92bcfff66d25e81df555c3151ef9d7e46275",
+    ".modelhub_state/outcome_checkpoint.json": "6da922ffa1e24e32d99de5d494e0389ed7d1c7ddb2faf8b442ad229fd476f1b4",
     ".modelhub_state/queue_cleanup_latest.json": "28912604a2c0333bff9534068068f84beba97443777662e1178ecc33bc24bb3c",
     ".modelhub_state/recent_outcomes.jsonl": "8600ee046a3f9f4a7dac9b245528302ead263dd0ae9e74dba232b8ac41e00541",
-    ".modelhub_state/recovery_active_tasks.jsonl": "f7d67ad71b10991cfb7feda05deaca22ad791e2802fd7fa1d923c7c2923a8ed1",
+    ".modelhub_state/recovery_active_tasks.jsonl": "9cda0e23fe77c96ea1234ac09476fdba6be0ab0e03be6f59f4998a0f684e0130",
-    ".modelhub_state/recovery_intents.jsonl": "a74c1ea40645552829f1f19d235212b156a9a6aaf0f626fb44423a656c443df6",
+    ".modelhub_state/recovery_intents.jsonl": "62006726f5f3758488a327da08410a72309b39910edba2e9e14142b98b4ad780",
     ".modelhub_state/routing_intelligence.json": "cdd3341d66484775862c4a1f5c766a7fc0200b1a3a204a76975162502e1d3457",
     ".modelhub_state/submission_exclusions.jsonl": "14480c58228be6b76e21e98008960b815d20d16132dcab7a11e5b449c5e2d220",
     ".modelhub_state/worker_crashes.jsonl": "9693a31a13cc18a3136ff5373f9569dc2fecaa274aaf91d3b1c8a67f31fe0162",
     "ledger/submissions.jsonl": "b7a4c9900ee212be7c7f8578a0a71942885eb83e97c5583098a169266bedf55c",
-    "outcomes/submissions.jsonl": "31c3531fa4d0bd6922da524b2b866aa22d1fbc324e130010c6ef5ccfc20b74ea"
+    "outcomes/submissions.jsonl": "25211d6c17253a387644ec0bcd58985093d59be097865b8e61cf8c81b74603f2"
   },
-  "generation": 6466,
+  "generation": 6467,
   "phase": "cycle",
   "schemaVersion": 1,
-  "updatedAt": "2026-09-13T02:02:42.996507+00:00",
+  "updatedAt": "2026-09-13T02:05:25.444159+00:00",
   "writerId": "e5dd59a4c84a4f21926bad61448789e2"
 }

outcomes/submissions.jsonl

@@ -34,7 +34,6 @@
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T15:14:29.722109+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality-FP16", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29952487299, "estimatedRequiredGiB": 33.498, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "manufacturer_spec", "sourceUrl": "https://www.birentech.com/news/id6rz98v3obczy77cmxzfgk3/"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 29973198172, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8027131120, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:m1", "custom_tag:m2", "custom_tag:fp16", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:coding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 29973198172}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T07:12:30.054811+00:00", "targetGpu": "Biren_166m", "taskId": "4621809", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-04T15:43:37.898131+00:00", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15338408461, "estimatedRequiredGiB": 17.168, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:8"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 15362064483, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7669052656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:exl3", "custom_tag:exllamav3", "custom_tag:quantization", "custom_tag:long-context", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "exl3", "repositoryOnDiskBytes": 15362064483}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T07:40:37.506061+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4622172", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-04T15:58:32.287733+00:00", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15338408461, "estimatedRequiredGiB": 17.168, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "published_card_spec", "sourceUrl": "https://aclanthology.org/2025.emnlp-main.1630.pdf"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 15362064483, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7669052656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:exl3", "custom_tag:exllamav3", "custom_tag:quantization", "custom_tag:long-context", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "exl3", "repositoryOnDiskBytes": 15362064483}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T07:56:50.952206+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4622417", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T16:14:29.511236+00:00", "modelId": "XHToken/Spark-X2.5-4B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8224192408, "estimatedRequiredGiB": 9.209, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:29"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 8239718512, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8239718512}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T08:10:58.161686+00:00", "targetGpu": "MetaX_c-500", "taskId": "4622625", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T16:14:29.511231+00:00", "modelId": "XHToken/Spark-X2.5-1.7B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3415340496, "estimatedRequiredGiB": 3.834, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:29"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 3430847031, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1707657216, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3430847031}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T08:10:58.162821+00:00", "targetGpu": "MetaX_c-500", "taskId": "4622620", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T16:14:29.511177+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727938576, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:29"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737300809, "modelscopeLicense": "other", "modelscopeParams": 8030261248, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737300809}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T08:10:58.185038+00:00", "targetGpu": "MetaX_c-500", "taskId": "4622623", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T16:14:29.511213+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:29"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737317601, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737317601}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T08:10:58.159820+00:00", "targetGpu": "MetaX_c-500", "taskId": "4622624", "taskType": "text-generation", "verifyResult": null}