state: generation 5012 (intent)
This commit is contained in:
@@ -1321,7 +1321,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-10T06:26:16.878922+00:00",
|
||||
"generatedAt": "2026-09-10T06:27:17.811722+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 66,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -416,7 +416,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-10T06:24:28.406679+00:00",
|
||||
"generatedAt": "2026-09-10T06:27:24.195683+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-10T06:18:23.451252+00:00",
|
||||
"lastSyncTime": "2026-09-10T06:18:23.199776+00:00",
|
||||
"generatedAt": "2026-09-10T06:27:17.787583+00:00",
|
||||
"lastSyncTime": "2026-09-10T06:27:17.610370+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -1876,10 +1876,10 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 23,
|
||||
"ambiguous_runtime": 24,
|
||||
"参数/模板问题": 1
|
||||
},
|
||||
"failureCount": 24,
|
||||
"failureCount": 25,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"pendingCount": 0,
|
||||
@@ -1889,8 +1889,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Kunlunxin_p-800",
|
||||
"taskType": "text-generation",
|
||||
"total": 24,
|
||||
"unresolvedFailureCount": 24
|
||||
"total": 25,
|
||||
"unresolvedFailureCount": 25
|
||||
},
|
||||
"MetaX_c-500|unknown|text-generation": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -2415,22 +2415,22 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 32,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 24,
|
||||
"ambiguous_runtime": 25,
|
||||
"framework_architecture_unsupported": 4,
|
||||
"model_load": 1,
|
||||
"platform_infrastructure": 1,
|
||||
"tokenizer_compatibility": 27,
|
||||
"参数/模板问题": 7
|
||||
},
|
||||
"failureCount": 64,
|
||||
"failureCount": 65,
|
||||
"failureRate": 1.0,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"total": 64,
|
||||
"unresolvedFailureCount": 31
|
||||
"total": 65,
|
||||
"unresolvedFailureCount": 32
|
||||
},
|
||||
"vllm_tokenizer_patch": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -2451,7 +2451,7 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-10T06:18:23.446969+00:00",
|
||||
"generatedAt": "2026-09-10T06:27:17.783721+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 26,
|
||||
@@ -2642,20 +2642,20 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 55,
|
||||
"ambiguous_runtime": 56,
|
||||
"memory_capacity": 1,
|
||||
"参数/模板问题": 1,
|
||||
"验证失败": 23
|
||||
},
|
||||
"failureCount": 80,
|
||||
"failureCount": 81,
|
||||
"failureRate": 1.0,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"total": 80,
|
||||
"unresolvedFailureCount": 79
|
||||
"total": 81,
|
||||
"unresolvedFailureCount": 80
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"attributableFailureCount": 39,
|
||||
@@ -3283,9 +3283,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 5
|
||||
"ambiguous_runtime": 6
|
||||
},
|
||||
"failureCount": 5,
|
||||
"failureCount": 6,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"modelType": "llama",
|
||||
@@ -3297,8 +3297,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Kunlunxin_p-800",
|
||||
"taskType": "text-generation",
|
||||
"total": 5,
|
||||
"unresolvedFailureCount": 5
|
||||
"total": 6,
|
||||
"unresolvedFailureCount": 6
|
||||
},
|
||||
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|phi3small|compressed-tensors": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -5892,6 +5892,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|llama|compressed-tensors|30": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"loadSizeLog2Bucket": 30,
|
||||
"modelType": "llama",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "compressed-tensors",
|
||||
"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|33": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -6877,15 +6901,15 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 1516,
|
||||
"totalRecords": 1603,
|
||||
"terminalRecords": 1517,
|
||||
"totalRecords": 1604,
|
||||
"totals": {
|
||||
"attributableFailureCount": 400,
|
||||
"decisionFailureRate": 0.8909,
|
||||
"decisionSuccessRate": 0.1091,
|
||||
"decisionTotal": 449,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 297,
|
||||
"ambiguous_runtime": 298,
|
||||
"backend_operator": 29,
|
||||
"framework_architecture_unsupported": 271,
|
||||
"memory_capacity": 11,
|
||||
@@ -6897,21 +6921,21 @@
|
||||
"参数/模板问题": 95,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1467,
|
||||
"failureCount": 1468,
|
||||
"failureRate": 0.9677,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 2,
|
||||
"successCount": 49,
|
||||
"successRate": 0.0323,
|
||||
"total": 1516,
|
||||
"unresolvedFailureCount": 1065
|
||||
"total": 1517,
|
||||
"unresolvedFailureCount": 1066
|
||||
},
|
||||
"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 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。",
|
||||
"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 +6943,7 @@
|
||||
"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 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 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 +6964,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 1603,
|
||||
"summarizedRecords": 1604,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -615,6 +615,8 @@
|
||||
{"batchId": "0eba3fbd543f4c7ca0de173706074663", "completedAt": "2026-09-10T06:13:04.904282+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-10T06:12:56.217191+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7e8cf575017b4b9d9a12ecc8d3557663", "lastModified": "2026-09-10T05:31:36+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-NVFP4", "reason": null, "reconciledAt": "2026-09-10T06:20:47.451553+00:00", "repoId": "primitive-ai/Nex-N2.5-mini-NVFP4", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "4754370", "taskType": "text-generation"}
|
||||
{"batchId": "0eba3fbd543f4c7ca0de173706074663", "completedAt": "2026-09-10T06:13:04.904301+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-10T06:12:56.217289+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e79c0ef4c2a048638b5e5d6f7970f3f1", "lastModified": "2026-09-10T05:36:14+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "reason": null, "reconciledAt": "2026-09-10T06:20:47.452223+00:00", "repoId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "4754369", "taskType": "text-generation"}
|
||||
{"batchId": "0eba3fbd543f4c7ca0de173706074663", "completedAt": "2026-09-10T06:13:04.904305+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-10T06:12:56.217342+00:00", "framework": "vllm", "intentId": "c5ca6bcddcca4c4498a1d0c93f75b529", "lastModified": "2026-09-10T05:34:35+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-FP8", "reason": null, "reconciledAt": "2026-09-10T06:20:47.451374+00:00", "repoId": "primitive-ai/Nex-N2.5-mini-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Mthreads_s4000", "taskId": "4754371", "taskType": "text-generation"}
|
||||
{"batchId": "8d1b53bc9ba9474ca3c99e943aabda33", "configFingerprint": "9ee85a9702ae695242c8b5436b1b856292d4a16c2f839d36bf93fbe98fb66d4e", "configSource": "modelhub_live", "createdAt": "2026-09-10T06:28:55.444531+00:00", "framework": "llamacpp", "intentId": "3ece1199138149888cbdee5d0236242f", "lastModified": "2026-09-10T05:46:18+00:00", "modelAddress": "https://modelscope.cn/models/bartowski/MiniCPM5-2B-GGUF", "repoId": "bartowski/MiniCPM5-2B-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Mthreads_s4000", "taskType": "text-generation"}
|
||||
{"batchId": "8d1b53bc9ba9474ca3c99e943aabda33", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-09-10T06:28:55.444637+00:00", "framework": "vllm", "intentId": "14625abdfeca4e868e1155c3bda46498", "lastModified": "2026-09-10T05:57:11+00:00", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-en-thinker", "repoId": "CohereLabs/tiny-aya-en-thinker", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation"}
|
||||
{"batchId": "93abbd86b4564ff2b94a94e46d15997c", "completedAt": "2026-09-10T02:01:15.152981+00:00", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-09-10T02:01:07.997982+00:00", "framework": "vllm", "intentId": "f62de0b86d234667845793d4dabba8be", "repoId": "nv-community/Qwen3.8-27B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "Iluvatar_mrv-100", "taskId": null, "taskType": "text-generation"}
|
||||
{"batchId": "60b640169cee4eb6aeaf36aa752d68d4", "completedAt": "2026-09-09T21:08:33.584377+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-09T21:08:21.304731+00:00", "framework": "vllm_fix_tokenizer", "intentId": "31500eb429ef4b3cbc844e4096a6b5f6", "repoId": "nv-community/Qwen3.8-27B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
|
||||
{"batchId": "395e59f0f1df48fcb2e0269b69d9bce5", "completedAt": "2026-09-09T16:24:21.684805+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-09T16:24:14.160686+00:00", "framework": "vllm", "intentId": "e2523fa4e63645688fd5e7c0c7c1a5d5", "repoId": "nv-community/Qwen3.8-27B-NVFP4", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "uniqueness_rejected", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
|
||||
|
||||
@@ -1,24 +1,24 @@
|
||||
{
|
||||
"agentVersion": "2026.09.04.4",
|
||||
"checksums": {
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "a97ed9a20a7bba758b1752d3c9f17b7f08aa9415141e9f559f62446560cf946b",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "5d2ae8c1394c8e6932b7d371db38ab576998866c723d83a48932a8f80c146dcb",
|
||||
".modelhub_state/architecture_history_backfill.json": "d60fc3f4fd5c9e6eb58b90fde1343dd1f0b6423c9fea96cf72aa38269ddc542b",
|
||||
".modelhub_state/market_intelligence.json": "769698df5b9b2fb141dde9304b565779364b60dcab9ec14c4febb435adeade34",
|
||||
".modelhub_state/official_capabilities.json": "ff7e7619587f0f217c0a617a6dd5d17ed1ac683335fae2cd4c1dfa65f34827bb",
|
||||
".modelhub_state/outcome_checkpoint.json": "7a14aaddb67a300941bfd7ae94da746f93f2cc8c7d308e1658ee549191a1f9d4",
|
||||
".modelhub_state/market_intelligence.json": "c4186909666357e8325776b13a4522c687fe6d639e399fcf8e8e04eb57f9dcb1",
|
||||
".modelhub_state/official_capabilities.json": "c2baa6a13760be0d3036b5df32f805c5ed05df87354e87da941447c404e5b1dc",
|
||||
".modelhub_state/outcome_checkpoint.json": "3efc6242a233c26184e650892d0e007c001adf9e1af898cdf73efd095b2379e8",
|
||||
".modelhub_state/queue_cleanup_latest.json": "b251e2ff52f1e826ed4fc9723e1765d93287b92341cb7f593f01eb5e88982f99",
|
||||
".modelhub_state/recent_outcomes.jsonl": "0349f991e1e1669c358319e65ce6a7cbc1fca49287207bd1f03243519925cc61",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "54910d4a7124718662b0e1349487e502bff6097151fdb46fe376be0bbafd6c0c",
|
||||
".modelhub_state/recovery_intents.jsonl": "c15a0871aff75251aec2276edc14020db8c5aea60572238c2b33abddd5a4b1b4",
|
||||
".modelhub_state/recovery_intents.jsonl": "a8feea137e6c81563935c6982bb9280388e1b341edfe38dd4773dac973341f12",
|
||||
".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": "cd01b975a75d1d85c148ccca69693dabfb9bda35c7510e904890531d02230077"
|
||||
"outcomes/submissions.jsonl": "3cf3e8e55a6e5bede217ab85e8001dc2545db0bef177fe654bec3c6afd090e26"
|
||||
},
|
||||
"generation": 5011,
|
||||
"phase": "cycle",
|
||||
"generation": 5012,
|
||||
"phase": "intent",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-09-10T06:26:16.945113+00:00",
|
||||
"updatedAt": "2026-09-10T06:28:55.504635+00:00",
|
||||
"writerId": "58ff5dc2a2d64b119ad1e4560700f977"
|
||||
}
|
||||
|
||||
@@ -208,7 +208,6 @@
|
||||
{"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": "2026-09-06T23:35:22.599877+00:00", "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2014810120, "estimatedRequiredGiB": 2.256, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2018195521, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1812039680, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2018195521}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T15:28:09.689378+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4669860", "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}
|
||||
|
||||
Reference in New Issue
Block a user