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

state: generation 5069 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-10 08:12:55 +00:00
parent 3bb648b31c
commit c09e3703ef
9 changed files with 2113 additions and 2115 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -1317,7 +1317,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-10T08:09:57.522701+00:00",
"generatedAt": "2026-09-10T08:12:54.160739+00:00",
"summary": {
"activeBlockCount": 66,
"byGpuFramework": {

6
.modelhub_state/architecture_history_backfill.json
View File

@@ -75,7 +75,7 @@
"7": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 359,
"listingErrors": 360,
"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": 7,
"nextAccountIndex": 8,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-10T08:09:57.498819+00:00",
"updatedAt": "2026-09-10T08:12:54.134541+00:00",
"version": 1
}

6
.modelhub_state/market_intelligence.json
View File

@@ -1,8 +1,8 @@
{
"communityAttemptedAt": "2026-09-10T07:53:17.152657+00:00",
"communityAttemptedAt": "2026-09-10T08:11:06.664506+00:00",
"communityError": null,
"communitySample": {},
"communityUpdatedAt": "2026-09-10T07:53:17.152657+00:00",
"communityUpdatedAt": "2026-09-10T08:11:06.664506+00:00",
"frameworkAttemptedAt": "2026-09-10T06:33:41.338309+00:00",
"frameworkError": null,
"frameworkStats": {
@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-10T08:08:04.265665+00:00",
"generatedAt": "2026-09-10T08:11:06.664506+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,

1506
.modelhub_state/official_capabilities.json
View File

File diff suppressed because it is too large Load Diff

76
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-10T08:02:07.265881+00:00",
"lastSyncTime": "2026-09-10T08:02:07.004701+00:00",
"generatedAt": "2026-09-10T08:10:58.477072+00:00",
"lastSyncTime": "2026-09-10T08:10:58.225916+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1872,10 +1872,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 25,
"ambiguous_runtime": 27,
"参数/模板问题": 1
},
"failureCount": 26,
"failureCount": 28,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -1885,8 +1885,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 26,
"unresolvedFailureCount": 26
"total": 28,
"unresolvedFailureCount": 28
},
"MetaX_c-500|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -2411,22 +2411,22 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 32,
"failureBreakdown": {
"ambiguous_runtime": 26,
"ambiguous_runtime": 28,
"framework_architecture_unsupported": 4,
"model_load": 1,
"platform_infrastructure": 1,
"tokenizer_compatibility": 27,
"参数/模板问题": 7
},
"failureCount": 66,
"failureCount": 68,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 0,
"successRate": 0.0,
"total": 66,
"unresolvedFailureCount": 33
"total": 68,
"unresolvedFailureCount": 35
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 0,
@@ -2447,7 +2447,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T08:02:07.261719+00:00",
"generatedAt": "2026-09-10T08:10:58.472731+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2638,20 +2638,20 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 57,
"ambiguous_runtime": 59,
"memory_capacity": 1,
"参数/模板问题": 1,
"验证失败": 23
},
"failureCount": 82,
"failureCount": 84,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 82,
"unresolvedFailureCount": 81
"total": 84,
"unresolvedFailureCount": 83
},
"MetaX_c-500": {
"attributableFailureCount": 40,
@@ -3279,9 +3279,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 7
"ambiguous_runtime": 9
},
"failureCount": 7,
"failureCount": 9,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "llama",
@@ -3293,8 +3293,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 7,
"unresolvedFailureCount": 7
"total": 9,
"unresolvedFailureCount": 9
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|phi3small|compressed-tensors": {
"attributableFailureCount": 0,
@@ -5918,9 +5918,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 32,
@@ -5933,8 +5933,8 @@
"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|llama|compressed-tensors|33": {
"attributableFailureCount": 0,
@@ -5942,9 +5942,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 4
"ambiguous_runtime": 5
},
"failureCount": 4,
"failureCount": 5,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 33,
@@ -5957,8 +5957,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 4,
"unresolvedFailureCount": 4
"total": 5,
"unresolvedFailureCount": 5
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|phi3small|compressed-tensors|33": {
"attributableFailureCount": 0,
@@ -6943,15 +6943,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1535,
"totalRecords": 1622,
"terminalRecords": 1537,
"totalRecords": 1624,
"totals": {
"attributableFailureCount": 401,
"decisionFailureRate": 0.8891,
"decisionSuccessRate": 0.1109,
"decisionTotal": 451,
"failureBreakdown": {
"ambiguous_runtime": 314,
"ambiguous_runtime": 316,
"backend_operator": 30,
"framework_architecture_unsupported": 271,
"memory_capacity": 11,
@@ -6963,21 +6963,21 @@
"参数/模板问题": 95,
"验证失败": 673
},
"failureCount": 1485,
"failureRate": 0.9674,
"failureCount": 1487,
"failureRate": 0.9675,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 50,
"successRate": 0.0326,
"total": 1535,
"unresolvedFailureCount": 1082
"successRate": 0.0325,
"total": 1537,
"unresolvedFailureCount": 1084
},
"warnings": [
"GPU Cambricon_mlu-370-x8 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 Iluvatar_mrv-100 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。",
"GPU Ascend_910-b4 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。",
@@ -6985,7 +6985,7 @@
"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 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-150 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-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 Biren_166m|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -7006,6 +7006,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1622,
"summarizedRecords": 1624,
"version": 1
}

1466
.modelhub_state/recovery_active_tasks.jsonl
View File

File diff suppressed because it is too large Load Diff

1144
.modelhub_state/recovery_intents.jsonl
View File

File diff suppressed because it is too large Load Diff

20
manifest.json
View File

@@ -1,24 +1,24 @@
{
"agentVersion": "2026.09.04.4",
"checksums": {
".modelhub_state/architecture_compatibility_blacklist.json": "5fe1dc0b79846be1df2264825627374c75bf644f13ae8282e6827c36923a5f9c",
".modelhub_state/architecture_history_backfill.json": "4cae10c87fad4c64733273b63b97f55168427d529c122b0cbbc7c234b4458a08",
".modelhub_state/market_intelligence.json": "f819e68d15d3fd0bdbf362ba121962ae50a10cf3567329b2b24af232bf0f5edd",
".modelhub_state/official_capabilities.json": "e54a3e416c63a7965af63411db53585748389d1dfb8c5f13954c89fb9f09ecb4",
".modelhub_state/outcome_checkpoint.json": "90675262b0d3cd3009abd1917a29a90cbee14dd51a312a5c46283387e2ce0d86",
".modelhub_state/architecture_compatibility_blacklist.json": "d5031ba5c6c67f5025e98249e87a61cf2e1dfc559f45cf33b6c255084844ddb8",
".modelhub_state/architecture_history_backfill.json": "b5d76180ef5da3928f1323be7c307063e359fb81e767d8de47b2efd0e94b9873",
".modelhub_state/market_intelligence.json": "34d1e39261d6fffad903e502f9fd91bf36e8c28668e9ffca4978f3e91042c5c8",
".modelhub_state/official_capabilities.json": "6f2e926cf6bd6e65b3091346efdec3a2a9ae83ceb66886175de79c8b6b0eca8f",
".modelhub_state/outcome_checkpoint.json": "076977b262052ae17f85c074e278e11328ef11e05265b3fc96cdadae9046e8a8",
".modelhub_state/queue_cleanup_latest.json": "b9038630dc67feced29c6931cb43d6d94c28bb175e6dcf80fac9c625a52887d5",
".modelhub_state/recent_outcomes.jsonl": "aabfa8b6cb55f991ed845ffcbec637ffab473f7f48b29e20b082818f5ee2dc00",
".modelhub_state/recovery_active_tasks.jsonl": "6026f08ffad693283dc6a9d2ea1ecc1bff15be1e462efa5cf83143ee058ecb0e",
".modelhub_state/recovery_intents.jsonl": "96b511edfc93b8bfe0485cef76827ad774dd049a308de606a7e2dcac50adbdc7",
".modelhub_state/recovery_active_tasks.jsonl": "2e301f22684edb04b91f0bd2a2f0074c83167d90aa9a0b31b5bd460ff444c688",
".modelhub_state/recovery_intents.jsonl": "143ff679abdf4440ef63da1a2bc6aeaf7e32af86e2c6d044054f1ad0c68de6c2",
".modelhub_state/routing_intelligence.json": "8a52419d4402861a79d360da797632830eb2c915c1cd189832eea085096de774",
".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03",
".modelhub_state/worker_crashes.jsonl": "d1c3f447ce0377ed5e820c2b5ff730d29f84a96af4fd14332b138f78c0ddde76",
"ledger/submissions.jsonl": "ae2d6630dc3b5048885517330e9530c50fe5e0c1ea4c5a17488ad884d16de042",
"outcomes/submissions.jsonl": "63123fb37e89e8bb42d6003a318dcdb692e3ccc7256bfca4f7c1671cf39e1633"
"outcomes/submissions.jsonl": "8882a18080eb10f2e0ee7ffd748b79bad4b115aa5cc223a86ad02b3abe39cfc7"
},
"generation": 5068,
"generation": 5069,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-10T08:09:57.628476+00:00",
"updatedAt": "2026-09-10T08:12:55.031347+00:00",
"writerId": "58ff5dc2a2d64b119ad1e4560700f977"
}

2
outcomes/submissions.jsonl
View File

@@ -203,10 +203,8 @@
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T22:33:26.815214+00:00", "modelId": "siliconflow/gpt-oss-20b-FP8", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22109595640, "estimatedRequiredGiB": 24.741, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 22137550529, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 20921584848, "modelscopeTags": ["license:Apache License 2.0", "model_type:gpt_oss", "library:safetensors", "library:other", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "mxfp4", "repositoryOnDiskBytes": 22137550529}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T14:32:32.785339+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4668538", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T22:43:37.806846+00:00", "modelId": "RedHatAI/Meta-Llama-3.1-70B-Instruct-FP8-dynamic", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 72669954704, "estimatedRequiredGiB": 81.225, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 72679220993, "modelscopeLicense": "llama3.1", "modelscopeParams": 70553706496, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 72679220993}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T14:33:50.986624+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4668642", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T22:43:37.806776+00:00", "modelId": "RedHatAI/starcoder2-3b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3484485728, "estimatedRequiredGiB": 3.898, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 3487786133, "modelscopeLicense": "other", "modelscopeParams": 3181366272, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3487786133}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T14:34:13.216402+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4668650", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T22:54:11.110176+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9081293776, "estimatedRequiredGiB": 10.159, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9090504091, "modelscopeLicense": "llama3", "modelscopeParams": 8030261312, "modelscopeTags": ["license:llama3", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9090504091}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T14:52:34.105196+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4668969", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T23:14:15.399910+00:00", "modelId": "zstack/qwen3-4b-fake", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 25165824, "estimatedRequiredGiB": 0.028, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 25169485, "modelscopeLicense": null, "modelscopeParams": 25165435, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 25169485}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T15:05:58.785747+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4669358", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T23:14:15.399880+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-FP8", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11910385168, "estimatedRequiredGiB": 13.339, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 11935116462, "modelscopeLicense": "mit", "modelscopeParams": 9409813744, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 11935116462}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T15:07:54.384483+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4669411", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T23:35:22.599825+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-ACTORDER-compressed-tensors-test", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5705684944, "estimatedRequiredGiB": 6.387, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5714910031, "modelscopeLicense": null, "modelscopeParams": 8031506432, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 5714910031}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T15:28:09.693682+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4669866", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T00:59:44.608188+00:00", "modelId": "RWKV/RWKV7-7.2B-20260805", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14399972864, "estimatedRequiredGiB": 16.095, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": 14402000339, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7199932416, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 14402000339}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T16:48:59.678173+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4672290", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T02:37:59.437424+00:00", "modelId": "RWKV/RWKV7-1.5B-20260805", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3055418240, "estimatedRequiredGiB": 3.417, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": 3057371034, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1527668736, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3057371034}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T18:34:36.628828+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4674757", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T03:57:59.407871+00:00", "modelId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306310880, "estimatedRequiredGiB": 21.599, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19326449341, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9653104368, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:transformers", "custom_tag:unsloth", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:distillation", "custom_tag:deepseek", "custom_tag:sft", "custom_tag:rl", "custom_tag:gspo", "custom_tag:math", "custom_tag:stem", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:mtp"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19326449341}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T19:48:32.773868+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4676609", "taskType": "text-generation", "verifyResult": null}