state: generation 24529 (cycle)

2026-10-14 01:56:56 +00:00
parent 662e872d3b
commit c7c7427492
8 changed files with 1924 additions and 1897 deletions
--- a/.modelhub_state/architecture_compatibility_blacklist.json
+++ b/.modelhub_state/architecture_compatibility_blacklist.json
@@ -2710,7 +2710,7 @@
      "taskType": "text-generation"
    }
  },
-  "generatedAt": "2026-10-14T01:47:41.554285+00:00",
+  "generatedAt": "2026-10-14T01:55:21.389542+00:00",
  "summary": {
    "activeBlockCount": 135,
    "byGpuFramework": {
--- a/.modelhub_state/market_intelligence.json
+++ b/.modelhub_state/market_intelligence.json
@@ -443,7 +443,7 @@
    }
  },
  "frameworkUpdatedAt": null,
-  "generatedAt": "2026-10-14T01:54:17.471453+00:00",
+  "generatedAt": "2026-10-14T01:56:48.145637+00:00",
  "gpuStats": {
    "Ascend_910-b3": {
      "available": true,
--- a/.modelhub_state/official_capabilities.json
+++ b/.modelhub_state/official_capabilities.json
@@ -1,5 +1,5 @@
 {
-  "catalogUpdatedAt": "2026-10-14T01:54:17.471453+00:00",
+  "catalogUpdatedAt": "2026-10-14T01:56:48.145637+00:00",
  "configuredTaskTypes": [
    "text-generation"
  ],
@@ -56,7 +56,7 @@
    "time-series-forecasting"
  ],
  "errors": [],
-  "generatedAt": "2026-10-14T01:54:19.569539+00:00",
+  "generatedAt": "2026-10-14T01:56:48.571648+00:00",
  "gpuCatalog": {
    "Ascend_910-b3": {
      "canVerify": true,
@@ -1384,14 +1384,6 @@
      ],
      "updatedAt": "2026-10-13T23:36:47.178229+00:00"
    },
-    "https://modelscope.cn/models/OpenBMB/MiniCPM-V-4.7-35B-A3B-DSpark|2026-10-12T18:20:45+00:00|Cambricon_mlu-370-x4": {
-      "taskTypes": [
-        "text-generation",
-        "text-to-image-generation",
-        "visual-multi-modal"
-      ],
-      "updatedAt": "2026-10-13T22:13:53.257972+00:00"
-    },
    "https://modelscope.cn/models/OpenBMB/MiniCPM-V-4.7-35B-A3B-DSpark|2026-10-12T18:20:45+00:00|Cambricon_mlu-370-x8": {
      "taskTypes": [
        "text-generation",
@@ -1430,6 +1422,14 @@
      ],
      "updatedAt": "2026-10-14T00:10:59.572539+00:00"
    },
+    "https://modelscope.cn/models/OpenBMB/MiniCPM-V-4.7-35B-A3B-DSpark|2026-10-12T18:20:45+00:00|hygon_k100-ai": {
+      "taskTypes": [
+        "text-generation",
+        "text-to-image-generation",
+        "visual-multi-modal"
+      ],
+      "updatedAt": "2026-10-14T01:56:48.571648+00:00"
+    },
    "https://modelscope.cn/models/SupraLabs/reasoning-summarizer-800m-pre-gguf|2026-10-12T21:20:41+00:00|Iluvatar_mrv-100": {
      "taskTypes": [
        "asr",
@@ -6564,6 +6564,6 @@
      "updateTime": "2025-12-22 08:59:53"
    }
  ],
-  "taskTreeUpdatedAt": "2026-10-14T01:54:17.471453+00:00",
+  "taskTreeUpdatedAt": "2026-10-14T01:56:48.145637+00:00",
  "version": 1
 }
--- a/.modelhub_state/outcome_checkpoint.json
+++ b/.modelhub_state/outcome_checkpoint.json
@@ -1,6 +1,6 @@
 {
-  "generatedAt": "2026-10-13T22:17:19.035058+00:00",
-  "lastSyncTime": "2026-10-13T22:17:18.970469+00:00",
+  "generatedAt": "2026-10-14T01:55:21.292114+00:00",
+  "lastSyncTime": "2026-10-14T01:55:21.057649+00:00",
  "recentLimit": 300,
  "report": {
    "architectureCompatibilityBlocks": {
@@ -2589,25 +2589,6 @@
        "targetGpu": "Sunrise_pt-200-x1",
        "taskType": "text-generation"
      },
-      "sunrise_pt-200-x1|vllm|text-generation|model_type:qwen3_5_moe": {
-        "architectureSignature": "model_type:qwen3_5_moe",
-        "architectures": [],
-        "evidenceCount": 1,
-        "expiresAt": "2026-10-14T00:43:21+00:00",
-        "framework": "vllm",
-        "latestFailureAt": "2026-09-14T00:43:21+00:00",
-        "latestSuccessfulAt": null,
-        "matchType": "model_type",
-        "modelType": "qwen3_5_moe",
-        "sourceModelIds": [
-          "apodex/Apodex-1.1-mini-GPTQ-Int4"
-        ],
-        "sourceTaskIds": [
-          "4490280"
-        ],
-        "targetGpu": "Sunrise_pt-200-x1",
-        "taskType": "text-generation"
-      },
      "vastai_va16|vllm_fix_tokenizer|text-generation|model_type:mini_k3": {
        "architectureSignature": "model_type:mini_k3",
        "architectures": [],
@@ -2734,7 +2715,7 @@
      }
    },
    "architectureCompatibilitySummary": {
-      "activeBlockCount": 136,
+      "activeBlockCount": 135,
      "byGpuFramework": {
        "Ascend_910-b3|vllm": 8,
        "Ascend_910-b3|vllm_tokenizer_patch": 10,
@@ -2757,7 +2738,7 @@
        "MetaX_c-500|vllm": 1,
        "MetaX_c-500|vllm_tokenizer_patch": 4,
        "Mthreads_s4000|vllm": 5,
-        "Sunrise_pt-200-x1|vllm": 2,
+        "Sunrise_pt-200-x1|vllm": 1,
        "Sunrise_pt-200-x1|vllm_fix_tokenizer": 2,
        "Vastai_va16|vllm": 4,
        "Vastai_va16|vllm_fix_tokenizer": 2,
@@ -4404,10 +4385,10 @@
        "decisionSuccessRate": 0.0,
        "decisionTotal": 0,
        "failureBreakdown": {
-          "ambiguous_runtime": 188,
+          "ambiguous_runtime": 189,
          "参数/模板问题": 7
        },
-        "failureCount": 195,
+        "failureCount": 196,
        "failureRate": 1.0,
        "framework": "vllm_fix_tokenizer",
        "pendingCount": 0,
@@ -4417,8 +4398,8 @@
        "successRate": 0.0,
        "targetGpu": "Kunlunxin_p-800",
        "taskType": "text-generation",
-        "total": 195,
-        "unresolvedFailureCount": 195
+        "total": 196,
+        "unresolvedFailureCount": 196
      },
      "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": {
        "attributableFailureCount": 61,
@@ -5591,7 +5572,7 @@
        "decisionSuccessRate": 0.0265,
        "decisionTotal": 189,
        "failureBreakdown": {
-          "ambiguous_runtime": 419,
+          "ambiguous_runtime": 420,
          "backend_operator": 11,
          "framework_architecture_unsupported": 53,
          "memory_capacity": 10,
@@ -5600,15 +5581,15 @@
          "tokenizer_compatibility": 97,
          "参数/模板问题": 23
        },
-        "failureCount": 657,
-        "failureRate": 0.9924,
+        "failureCount": 658,
+        "failureRate": 0.9925,
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 31,
        "successCount": 5,
-        "successRate": 0.0076,
-        "total": 662,
-        "unresolvedFailureCount": 442
+        "successRate": 0.0075,
+        "total": 663,
+        "unresolvedFailureCount": 443
      },
      "vllm_tokenizer_patch": {
        "attributableFailureCount": 170,
@@ -5639,7 +5620,7 @@
        "unresolvedFailureCount": 336
      }
    },
-    "generatedAt": "2026-10-13T22:17:19.022868+00:00",
+    "generatedAt": "2026-10-14T01:55:21.279011+00:00",
    "gpuSummaries": {
      "Ascend_910-b3": {
        "attributableFailureCount": 130,
@@ -5871,7 +5852,7 @@
        "decisionSuccessRate": 0.066,
        "decisionTotal": 106,
        "failureBreakdown": {
-          "ambiguous_runtime": 277,
+          "ambiguous_runtime": 278,
          "backend_operator": 23,
          "framework_architecture_unsupported": 37,
          "memory_capacity": 3,
@@ -5884,15 +5865,15 @@
          "日志缺失": 1,
          "验证失败": 23
        },
-        "failureCount": 452,
-        "failureRate": 0.9847,
+        "failureCount": 453,
+        "failureRate": 0.9848,
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 1,
        "successCount": 7,
-        "successRate": 0.0153,
-        "total": 459,
-        "unresolvedFailureCount": 352
+        "successRate": 0.0152,
+        "total": 460,
+        "unresolvedFailureCount": 353
      },
      "Kunlunxin_r-200-8f": {
        "attributableFailureCount": 0,
@@ -19213,6 +19194,29 @@
        "total": 4,
        "unresolvedFailureCount": 4
      },
+      "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_moe|modelopt": {
+        "attributableFailureCount": 0,
+        "decisionFailureRate": 0.0,
+        "decisionSuccessRate": 0.0,
+        "decisionTotal": 0,
+        "failureBreakdown": {
+          "ambiguous_runtime": 1
+        },
+        "failureCount": 1,
+        "failureRate": 1.0,
+        "framework": "vllm_fix_tokenizer",
+        "modelType": "qwen3_5_moe",
+        "pendingCount": 0,
+        "pendingRate": 0.0,
+        "platformFailureCount": 0,
+        "quantizationMethod": "modelopt",
+        "successCount": 0,
+        "successRate": 0.0,
+        "targetGpu": "Kunlunxin_p-800",
+        "taskType": "text-generation",
+        "total": 1,
+        "unresolvedFailureCount": 1
+      },
      "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none": {
        "attributableFailureCount": 0,
        "decisionFailureRate": 0.0,
@@ -48308,6 +48312,30 @@
        "total": 4,
        "unresolvedFailureCount": 4
      },
+      "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_moe|modelopt|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": "qwen3_5_moe",
+        "pendingCount": 0,
+        "pendingRate": 0.0,
+        "platformFailureCount": 0,
+        "quantizationMethod": "modelopt",
+        "successCount": 0,
+        "successRate": 0.0,
+        "targetGpu": "Kunlunxin_p-800",
+        "taskType": "text-generation",
+        "total": 1,
+        "unresolvedFailureCount": 1
+      },
      "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none|33": {
        "attributableFailureCount": 0,
        "decisionFailureRate": 0.0,
@@ -59309,15 +59337,15 @@
        "unresolvedFailureCount": 0
      }
    },
-    "terminalRecords": 17865,
-    "totalRecords": 18394,
+    "terminalRecords": 17866,
+    "totalRecords": 18395,
    "totals": {
      "attributableFailureCount": 6325,
      "decisionFailureRate": 0.8655,
      "decisionSuccessRate": 0.1345,
      "decisionTotal": 7308,
      "failureBreakdown": {
-        "ambiguous_runtime": 4637,
+        "ambiguous_runtime": 4638,
        "architecture_compatibility": 212,
        "attention_backend": 3,
        "backend_operator": 132,
@@ -59333,31 +59361,31 @@
        "日志缺失": 719,
        "验证失败": 676
      },
-      "failureCount": 16882,
+      "failureCount": 16883,
      "failureRate": 0.945,
      "pendingCount": 0,
      "pendingRate": 0.0,
      "platformFailureCount": 964,
      "successCount": 983,
      "successRate": 0.055,
-      "total": 17865,
-      "unresolvedFailureCount": 9593
+      "total": 17866,
+      "unresolvedFailureCount": 9594
    },
    "warnings": [
      "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 Sunrise_pt-200-x1 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 MetaX_c-500 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 Iluvatar_bi-100 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 Ascend_910-b3 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 Iluvatar_mrv-100 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 MetaX_c-500 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 Vastai_va16|vllm_fix_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 Iluvatar_bi-150|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。",
      "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。",
@@ -59403,6 +59431,6 @@
    ]
  },
  "storageMode": "decision_state_only",
-  "summarizedRecords": 18394,
+  "summarizedRecords": 18395,
  "version": 1
 }
--- a/.modelhub_state/recovery_active_tasks.jsonl
+++ b/.modelhub_state/recovery_active_tasks.jsonl
--- a/.modelhub_state/recovery_intents.jsonl
+++ b/.modelhub_state/recovery_intents.jsonl
--- a/manifest.json
+++ b/manifest.json
@@ -2,24 +2,24 @@
  "agentVersion": "2026.09.04.4",
  "checksums": {
    ".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1",
-    ".modelhub_state/architecture_compatibility_blacklist.json": "7d254914ada6229d70fb6010c3a3af526b0656dc651fcda5ab23d79221b149dd",
+    ".modelhub_state/architecture_compatibility_blacklist.json": "f99167577da21e4c40ce172b870b128c27d2229a1672c0f2de0eca8fdd33cc5b",
    ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
-    ".modelhub_state/market_intelligence.json": "18d308eb708460ac5973d3aab922ec22d475a3fbcd137183f2924aa83b974ecd",
-    ".modelhub_state/official_capabilities.json": "2d81c4ed0797371ed8e8dcb4951331d05f4b89671869cdd0abc6f978a43ceb63",
-    ".modelhub_state/outcome_checkpoint.json": "11bd6657f10c10dce8ce8d6d018569e42c523b9babca1d11689dfecd2c36af12",
+    ".modelhub_state/market_intelligence.json": "3ad51621dd01dd306e6c3f897bd141138de07be3d1744f2fb2e42d602d868f58",
+    ".modelhub_state/official_capabilities.json": "455ff4754b0da82e7ad9635093f8f35259a4c8dfde2af813e3e56dc620255004",
+    ".modelhub_state/outcome_checkpoint.json": "4d779101ca34c2a85350b599cd835a38fb151c7660fa89189bbde48df3c730a2",
    ".modelhub_state/queue_cleanup_latest.json": "76b23f67feac318ec0c94a1c929622b58cf0a8b1be5a6805610d677066854201",
    ".modelhub_state/recent_outcomes.jsonl": "f140f32fe2dfebd3c84d5dae02f318bab3dc350b5d57daa1e908e7a53a9bc4f9",
-    ".modelhub_state/recovery_active_tasks.jsonl": "5adb1ab8d221709fa92cc8ca6e2388661cc809db1a95bc8c8ef2987f49fa026f",
-    ".modelhub_state/recovery_intents.jsonl": "e76160268c51aec26c67d9d547435395fe4bb71690b1421e446e2b8f3b9e9078",
+    ".modelhub_state/recovery_active_tasks.jsonl": "3332360b667765dbef3060ca225a705f296e984d0ead21816d006e44f624d31b",
+    ".modelhub_state/recovery_intents.jsonl": "0005c9849edf96c7a4b236b84867a30c87c7c5fd4903f58c0530bfe0df13395b",
    ".modelhub_state/routing_intelligence.json": "8020ddd6b21b3ae60209338abbece8ff6c0019d37c1ea608f2e9899fbf57328e",
    ".modelhub_state/submission_exclusions.jsonl": "660ad77b924d3b0cc76f46aacd1f91a924d13a02bc68057eb5a964647441283b",
    ".modelhub_state/worker_crashes.jsonl": "a6b56caed5c7afeb803f8701393cf4660f7e9799eb5ff84af826a142e16d9b00",
    "ledger/submissions.jsonl": "3db0efee45fcae9867b7002e7e0ae586c0be197c909225bd7cdfe4b75772c939",
-    "outcomes/submissions.jsonl": "0fbe50195e0223a8b5333ee241365e1a4250d32391f6e2e3345af2ffadc62b92"
+    "outcomes/submissions.jsonl": "3d6e77f69e6a9a78415d0338c336b517ddd4025ba854ecf9b383ba99c5fd6a64"
  },
-  "generation": 24528,
+  "generation": 24529,
  "phase": "cycle",
  "schemaVersion": 1,
-  "updatedAt": "2026-10-14T01:54:20.101936+00:00",
+  "updatedAt": "2026-10-14T01:56:56.712721+00:00",
  "writerId": "0b4d13138a434e929040a457f5ff8e93"
 }
--- a/outcomes/submissions.jsonl
+++ b/outcomes/submissions.jsonl
@@ -282,7 +282,6 @@
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-29T02:56:17.459578+00:00", "modelId": "BananaMind/TernaryBananaMind-10M", "modelProfile": {"architectures": ["BananaAllForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.04, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bananaall", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:bananaall", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:small-language-model", "custom_tag:bananamind", "custom_tag:bananamind2", "custom_tag:ternary", "custom_tag:int8-embeddings", "custom_tag:digit-tokenizer", "custom_tag:pytorch", "custom_tag:safetensors", "custom_tag:custom-code", "custom_tag:trust-remote-code", "custom_tag:custom-architecture"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 36069420}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-28T18:50:52.450333+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5154463", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-29T02:56:17.459609+00:00", "modelId": "peculiar-ragdoll/Sharp-MiniCPM5-2B-MLX-oQ6e", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2092366914, "estimatedRequiredGiB": 2.351, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:omlx", "custom_tag:apple-silicon", "custom_tag:oq", "custom_tag:llama", "custom_tag:minicpm", "custom_tag:imatrix", "custom_tag:long-context", "custom_tag:coding", "custom_tag:sharp-template", "custom_tag:6-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2103475788}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-28T18:50:52.443583+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5154462", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-29T03:14:36.161396+00:00", "modelId": "juspay/xor-lite", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:typed-classification"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043603436}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-28T19:07:04.785610+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5154635", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-29T03:14:36.161378+00:00", "modelId": "juspay/xor-nvfp4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 41817852712, "estimatedRequiredGiB": 46.768, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 15008654192, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:mixture-of-experts", "custom_tag:typed-classification", "custom_tag:nvfp4", "custom_tag:modelopt", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 41847485419}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-28T19:07:04.848603+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5154636", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-29T03:14:36.161388+00:00", "modelId": "BananaMind/TernaryBananaMind-10M", "modelProfile": {"architectures": ["BananaAllForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.04, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bananaall", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:bananaall", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:small-language-model", "custom_tag:bananamind", "custom_tag:bananamind2", "custom_tag:ternary", "custom_tag:int8-embeddings", "custom_tag:digit-tokenizer", "custom_tag:pytorch", "custom_tag:safetensors", "custom_tag:custom-code", "custom_tag:trust-remote-code", "custom_tag:custom-architecture"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 36069420}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-28T19:08:37.345036+00:00", "targetGpu": "Vastai_va16", "taskId": "5154643", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-29T03:14:36.161347+00:00", "modelId": "peculiar-ragdoll/Sharp-MiniCPM5-2B-MLX-oQ6e", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2092366914, "estimatedRequiredGiB": 2.351, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:omlx", "custom_tag:apple-silicon", "custom_tag:oq", "custom_tag:llama", "custom_tag:minicpm", "custom_tag:imatrix", "custom_tag:long-context", "custom_tag:coding", "custom_tag:sharp-template", "custom_tag:6-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2103475788}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-28T19:08:37.352167+00:00", "targetGpu": "Vastai_va16", "taskId": "5154642", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-29T03:24:28.551006+00:00", "modelId": "juspay/xor-lite", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:typed-classification"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043603436}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-28T19:24:03.456200+00:00", "targetGpu": "Vastai_va16", "taskId": "5154910", "taskType": "text-generation", "verifyResult": null}