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

state: generation 5009 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-10 06:20:47 +00:00
parent 810788f16e
commit f944807983
9 changed files with 2110 additions and 2109 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -1321,7 +1321,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-10T06:17:22.308752+00:00",
"generatedAt": "2026-09-10T06:20:46.834056+00:00",
"summary": {
"activeBlockCount": 66,
"byGpuFramework": {

6
.modelhub_state/architecture_history_backfill.json
View File

@@ -11,7 +11,7 @@
"1": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 356,
"listingErrors": 357,
"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": 1,
"nextAccountIndex": 2,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-10T06:17:22.285825+00:00",
"updatedAt": "2026-09-10T06:20:46.807689+00:00",
"version": 1
}

6
.modelhub_state/market_intelligence.json
View File

@@ -1,8 +1,8 @@
{
"communityAttemptedAt": "2026-09-10T06:01:39.033026+00:00",
"communityAttemptedAt": "2026-09-10T06:18:33.879186+00:00",
"communityError": null,
"communitySample": {},
"communityUpdatedAt": "2026-09-10T06:01:39.033026+00:00",
"communityUpdatedAt": "2026-09-10T06:18:33.879186+00:00",
"frameworkAttemptedAt": "2026-09-10T00:33:23.734278+00:00",
"frameworkError": null,
"frameworkStats": {
@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-10T06:15:52.441602+00:00",
"generatedAt": "2026-09-10T06:18:33.879186+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,

1536
.modelhub_state/official_capabilities.json
View File

File diff suppressed because it is too large Load Diff

64
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-10T06:11:26.387915+00:00",
"lastSyncTime": "2026-09-10T06:11:26.144205+00:00",
"generatedAt": "2026-09-10T06:18:23.451252+00:00",
"lastSyncTime": "2026-09-10T06:18:23.199776+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1876,10 +1876,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 22,
"ambiguous_runtime": 23,
"参数/模板问题": 1
},
"failureCount": 23,
"failureCount": 24,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -1889,8 +1889,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 23,
"unresolvedFailureCount": 23
"total": 24,
"unresolvedFailureCount": 24
},
"MetaX_c-500|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -2415,22 +2415,22 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 32,
"failureBreakdown": {
"ambiguous_runtime": 23,
"ambiguous_runtime": 24,
"framework_architecture_unsupported": 4,
"model_load": 1,
"platform_infrastructure": 1,
"tokenizer_compatibility": 27,
"参数/模板问题": 7
},
"failureCount": 63,
"failureCount": 64,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 0,
"successRate": 0.0,
"total": 63,
"unresolvedFailureCount": 30
"total": 64,
"unresolvedFailureCount": 31
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 0,
@@ -2451,7 +2451,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T06:11:26.383978+00:00",
"generatedAt": "2026-09-10T06:18:23.446969+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2642,20 +2642,20 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 54,
"ambiguous_runtime": 55,
"memory_capacity": 1,
"参数/模板问题": 1,
"验证失败": 23
},
"failureCount": 79,
"failureCount": 80,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 79,
"unresolvedFailureCount": 78
"total": 80,
"unresolvedFailureCount": 79
},
"MetaX_c-500": {
"attributableFailureCount": 39,
@@ -3283,9 +3283,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 4
"ambiguous_runtime": 5
},
"failureCount": 4,
"failureCount": 5,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "llama",
@@ -3297,8 +3297,8 @@
"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": {
"attributableFailureCount": 0,
@@ -5898,9 +5898,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 3
"ambiguous_runtime": 4
},
"failureCount": 3,
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 33,
@@ -5913,8 +5913,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 3,
"unresolvedFailureCount": 3
"total": 4,
"unresolvedFailureCount": 4
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|phi3small|compressed-tensors|33": {
"attributableFailureCount": 0,
@@ -6877,15 +6877,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1515,
"totalRecords": 1602,
"terminalRecords": 1516,
"totalRecords": 1603,
"totals": {
"attributableFailureCount": 400,
"decisionFailureRate": 0.8909,
"decisionSuccessRate": 0.1091,
"decisionTotal": 449,
"failureBreakdown": {
"ambiguous_runtime": 296,
"ambiguous_runtime": 297,
"backend_operator": 29,
"framework_architecture_unsupported": 271,
"memory_capacity": 11,
@@ -6897,21 +6897,21 @@
"参数/模板问题": 95,
"验证失败": 673
},
"failureCount": 1466,
"failureCount": 1467,
"failureRate": 0.9677,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 49,
"successRate": 0.0323,
"total": 1515,
"unresolvedFailureCount": 1064
"total": 1516,
"unresolvedFailureCount": 1065
},
"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。",
@@ -6919,7 +6919,7 @@
"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。",
@@ -6940,6 +6940,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1602,
"summarizedRecords": 1603,
"version": 1
}

1460
.modelhub_state/recovery_active_tasks.jsonl
View File

File diff suppressed because it is too large Load Diff

1124
.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": "f6e614bec321983041e3f6b7b43c17917bc470559d148a671707e6cc9ea30c61",
".modelhub_state/architecture_history_backfill.json": "92eb441462b051477e4cd3a8b359d9d5d1652e3fbb842e3f39aece0b84efbbcb",
".modelhub_state/market_intelligence.json": "19e37b737ce1ba14463b4a83ee26756845aa39a8d32f3d2f0d4693523632ecb0",
".modelhub_state/official_capabilities.json": "8453b1ec01e380c2e6b3a7f55cb2521cbd41f1129383f0c94f580474c9ab550f",
".modelhub_state/outcome_checkpoint.json": "77ea43024f37c4155a2e3d0b828d19b8b806d488bc09aeb352825cec0a7c028e",
".modelhub_state/architecture_compatibility_blacklist.json": "1ae6a73157c3d537b3d7160ea4e8dcc7354f5cfe811b14ba4e9a2a960d2db8e4",
".modelhub_state/architecture_history_backfill.json": "4ff2710e6b0df6f1e76f135cd58400ce3e604c1f29703d3b24c8dda853d830cd",
".modelhub_state/market_intelligence.json": "530565254247fe9f3111bd6d20bc86d4b45db845b1c011f5dee36939c8f3aa63",
".modelhub_state/official_capabilities.json": "5f0ce4e497f4d84b45877389e3fd87f576ca0df558474c4913e1e99c14858e3a",
".modelhub_state/outcome_checkpoint.json": "7a14aaddb67a300941bfd7ae94da746f93f2cc8c7d308e1658ee549191a1f9d4",
".modelhub_state/queue_cleanup_latest.json": "b251e2ff52f1e826ed4fc9723e1765d93287b92341cb7f593f01eb5e88982f99",
".modelhub_state/recent_outcomes.jsonl": "0349f991e1e1669c358319e65ce6a7cbc1fca49287207bd1f03243519925cc61",
".modelhub_state/recovery_active_tasks.jsonl": "83463c8cc8998fb10af066c95d837a76618254ff9a22186c5e8a12e9f012f144",
".modelhub_state/recovery_intents.jsonl": "39e541b11456994e99f4b412706b2bd29eb6afee8e330ad3bdf1ac37aaf2552d",
".modelhub_state/recovery_active_tasks.jsonl": "54910d4a7124718662b0e1349487e502bff6097151fdb46fe376be0bbafd6c0c",
".modelhub_state/recovery_intents.jsonl": "c15a0871aff75251aec2276edc14020db8c5aea60572238c2b33abddd5a4b1b4",
".modelhub_state/routing_intelligence.json": "549eb329d3e9a8db0838eecf794503cbe4d6c9f895c4b96ea058ae45ff152816",
".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03",
".modelhub_state/worker_crashes.jsonl": "d1c3f447ce0377ed5e820c2b5ff730d29f84a96af4fd14332b138f78c0ddde76",
"ledger/submissions.jsonl": "0efc8df452e34c910ff9b4ceb943d429ac7c2dbd41fe343ae27da4952ddb6de0",
"outcomes/submissions.jsonl": "f02558d56c73aa9fc35e191b4d62414f963363bd835974bc43f5ca8af37a4f2a"
"outcomes/submissions.jsonl": "cd01b975a75d1d85c148ccca69693dabfb9bda35c7510e904890531d02230077"
},
"generation": 5008,
"generation": 5009,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-10T06:17:22.379826+00:00",
"updatedAt": "2026-09-10T06:20:47.569091+00:00",
"writerId": "58ff5dc2a2d64b119ad1e4560700f977"
}

1
outcomes/submissions.jsonl
View File

@@ -203,7 +203,6 @@
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T22:04:22.613054+00:00", "modelId": "neuralmagic/Meta-Llama-3.1-70B-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 72656575880, "estimatedRequiredGiB": 81.21, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 72665883326, "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": 72665883326}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T13:58:59.550329+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4667927", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T22:04:22.613090+00:00", "modelId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26119812080, "estimatedRequiredGiB": 29.233, "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": 26156887523, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:apodex", "custom_tag:arxiv:2608.23283"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26156887523}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T14:01:57.388649+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4668028", "taskType": "text-generation", "verifyResult": null}
{"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": "2026-09-06T22:33:26.815256+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084014480, "estimatedRequiredGiB": 10.162, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093198689, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093198689}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T14:32:40.056825+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4668539", "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}