state: generation 10419 (intent)

This commit is contained in:
2026-09-20 09:10:31 +00:00
parent 02716a4c2c
commit fdef535ed4
7 changed files with 2325 additions and 2222 deletions

View File

@@ -1783,7 +1783,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-20T08:57:51.173531+00:00",
"generatedAt": "2026-09-20T09:09:45.561740+00:00",
"summary": {
"activeBlockCount": 86,
"byGpuFramework": {

View File

@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-20T09:09:08.232789+00:00",
"generatedAt": "2026-09-20T09:09:45.571586+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,

File diff suppressed because it is too large Load Diff

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-20T08:31:30.745590+00:00",
"lastSyncTime": "2026-09-20T08:31:30.458816+00:00",
"generatedAt": "2026-09-20T09:09:45.514906+00:00",
"lastSyncTime": "2026-09-20T09:09:44.603509+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -3258,10 +3258,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 78,
"ambiguous_runtime": 80,
"参数/模板问题": 2
},
"failureCount": 80,
"failureCount": 82,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -3271,8 +3271,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 80,
"unresolvedFailureCount": 80
"total": 82,
"unresolvedFailureCount": 82
},
"Kunlunxin_r-200-8f|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -4326,7 +4326,7 @@
"decisionSuccessRate": 0.0179,
"decisionTotal": 112,
"failureBreakdown": {
"ambiguous_runtime": 88,
"ambiguous_runtime": 90,
"backend_operator": 8,
"framework_architecture_unsupported": 19,
"model_load": 1,
@@ -4334,15 +4334,15 @@
"tokenizer_compatibility": 82,
"参数/模板问题": 8
},
"failureCount": 222,
"failureRate": 0.9911,
"failureCount": 224,
"failureRate": 0.9912,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 16,
"successCount": 2,
"successRate": 0.0089,
"total": 224,
"unresolvedFailureCount": 96
"successRate": 0.0088,
"total": 226,
"unresolvedFailureCount": 98
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 23,
@@ -4364,7 +4364,7 @@
"unresolvedFailureCount": 23
}
},
"generatedAt": "2026-09-20T08:31:30.738700+00:00",
"generatedAt": "2026-09-20T09:09:45.508557+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 72,
@@ -4592,21 +4592,21 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 151,
"ambiguous_runtime": 153,
"memory_capacity": 1,
"参数/模板问题": 2,
"日志缺失": 1,
"验证失败": 23
},
"failureCount": 178,
"failureCount": 180,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 178,
"unresolvedFailureCount": 177
"total": 180,
"unresolvedFailureCount": 179
},
"Kunlunxin_r-200-8f": {
"attributableFailureCount": 0,
@@ -7736,9 +7736,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
"ambiguous_runtime": 4
},
"failureCount": 2,
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "qwen3_5_moe",
@@ -7750,8 +7750,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
"total": 4,
"unresolvedFailureCount": 4
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none": {
"attributableFailureCount": 0,
@@ -15107,9 +15107,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
"ambiguous_runtime": 4
},
"failureCount": 2,
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 34,
@@ -15122,8 +15122,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
"total": 4,
"unresolvedFailureCount": 4
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none|34": {
"attributableFailureCount": 0,
@@ -18252,15 +18252,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 15769,
"totalRecords": 15872,
"terminalRecords": 15771,
"totalRecords": 15874,
"totals": {
"attributableFailureCount": 5707,
"decisionFailureRate": 0.8614,
"decisionSuccessRate": 0.1386,
"decisionTotal": 6625,
"failureBreakdown": {
"ambiguous_runtime": 3720,
"ambiguous_runtime": 3722,
"architecture_compatibility": 212,
"attention_backend": 1,
"backend_operator": 101,
@@ -18276,15 +18276,15 @@
"日志缺失": 719,
"验证失败": 673
},
"failureCount": 14851,
"failureCount": 14853,
"failureRate": 0.9418,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 922,
"successCount": 918,
"successRate": 0.0582,
"total": 15769,
"unresolvedFailureCount": 8222
"total": 15771,
"unresolvedFailureCount": 8224
},
"warnings": [
"GPU Iluvatar_bi-100 本地统计失败率偏高(≥50%),建议重点关注。",
@@ -18327,13 +18327,13 @@
"组合 Ascend_910-b3|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 Cambricon_mlu-370-x4|unknown|visual-multi-modal 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Ascend_910-b4|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"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 Cambricon_mlu-370-x8|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 Iluvatar_mrv-100|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Ascend_910-b3|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 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 Ascend_910-b3|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。"
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 15872,
"summarizedRecords": 15874,
"version": 1
}

View File

@@ -1596,6 +1596,67 @@
{"batchId": "32beace4dd824c5f99caf15f71cacef7", "completedAt": "2026-09-20T09:07:26.792812+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:00:59.214011+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6800271ece9d4b2685084eef33b529df", "lastModified": "2026-09-01T03:45:04+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8", "reason": null, "reconciledAt": "2026-09-20T09:09:41.757476+00:00", "repoId": "primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Iluvatar_bi-150", "taskId": "4974425", "taskType": "text-generation"}
{"batchId": "32beace4dd824c5f99caf15f71cacef7", "completedAt": "2026-09-20T09:07:26.792830+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:00:59.214339+00:00", "framework": "transformers", "intentId": "67d0c946aa33456897b905774ea87097", "lastModified": "2026-08-26T18:34:54+00:00", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B-NVFP4", "reason": null, "reconciledAt": "2026-09-20T09:09:41.753118+00:00", "repoId": "ornith-ai/Ornith-1.5-9B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Iluvatar_bi-150", "taskId": "4974501", "taskType": "text-generation"}
{"batchId": "4167375da4e14cd28313058231752f71", "completedAt": "2026-09-20T09:09:39.770893+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:09:31.628872+00:00", "framework": "vllm", "intentId": "91414bd72b2f45d8ad775546fe4d8013", "lastModified": "2026-09-19T14:40:27+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "reason": null, "reconciledAt": "2026-09-20T09:09:41.754060+00:00", "repoId": "solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4974664", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.894307+00:00", "framework": "vllm_tokenizer_patch", "intentId": "474808f0dacf4a08a554e99eb62bdafe", "lastModified": "2026-08-24T20:05:18+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.894428+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7dbfc9f3cac14161a814801991c049a2", "lastModified": "2026-08-24T19:59:13+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-FP8", "repoId": "RedHatAI/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.894482+00:00", "framework": "vllm", "intentId": "f94d00a69f7e4e4888974c47b4bec4af", "lastModified": "2026-09-04T14:33:33+00:00", "modelAddress": "https://modelscope.cn/models/amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "repoId": "amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.894532+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ed1b622e1fa74a4ebdddc14003952d0f", "lastModified": "2026-08-24T20:04:01+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "repoId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.894574+00:00", "framework": "vllm_tokenizer_patch", "intentId": "aa97eebbf96c4c709de6046904101220", "lastModified": "2026-08-24T19:57:49+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.894614+00:00", "framework": "vllm_tokenizer_patch", "intentId": "66849a735caa487895c2eef319478dac", "lastModified": "2026-08-24T20:09:59+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Llama-2-7b-chat-quantized.w8a8", "repoId": "neuralmagic/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.894652+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ab64f9fc542c4e708461cd03929d582d", "lastModified": "2026-08-24T20:01:20+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "repoId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.894703+00:00", "framework": "vllm_tokenizer_patch", "intentId": "effb7689c46f41e7873ce81ae5e6c145", "lastModified": "2026-08-24T19:54:53+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Llama-3.2-3B-Instruct-FP8", "repoId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.894741+00:00", "framework": "vllm_tokenizer_patch", "intentId": "772aa49ff9d04c47a669d89ffc525ca3", "lastModified": "2026-08-24T20:15:22+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Llama-3.2-1B-Instruct-quantized.w8a8", "repoId": "RedHatAI/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.894780+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f5564899090b4ca19fa9d08540816763", "lastModified": "2026-08-24T20:09:49+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Llama-3.2-3B-Instruct-FP8", "repoId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.894819+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c7950883212a415ea95b1fb4655c891a", "lastModified": "2026-08-24T20:17:00+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.894857+00:00", "framework": "vllm_tokenizer_patch", "intentId": "324f4fd2f8614e7bbbafc6bfc3a39558", "lastModified": "2026-08-24T20:10:55+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-quantized.w8a8", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.894896+00:00", "framework": "vllm_tokenizer_patch", "intentId": "062c6d6cdbab4c31b6b0e784c5e5c615", "lastModified": "2026-08-24T20:08:44+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.894934+00:00", "framework": "vllm_tokenizer_patch", "intentId": "015e29d245ed4404924a0ef741740a55", "lastModified": "2026-08-24T20:01:57+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-it-quantized.w4a16", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.894973+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ceaeb93724244d509251a5cc97efcc78", "lastModified": "2026-08-24T20:02:01+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-quantized.w8a16", "repoId": "RedHatAI/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.895012+00:00", "framework": "vllm_tokenizer_patch", "intentId": "eddbcb3f9ebe4f94bbe9824782b59b46", "lastModified": "2026-08-24T20:06:34+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-3b-quantized.w8a8", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.895050+00:00", "framework": "vllm_tokenizer_patch", "intentId": "fdcbd48e8643482f8d138020cec34943", "lastModified": "2026-08-24T20:02:14+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-it-quantized.w8a16", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.895088+00:00", "framework": "vllm-mlu", "intentId": "34c1b86d92a9496da80c0114b6289497", "lastModified": "2026-08-26T19:43:40+00:00", "modelAddress": "https://modelscope.cn/models/inceptionai/Jais-2-8B-Chat", "repoId": "inceptionai/Jais-2-8B-Chat", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.895157+00:00", "framework": "vllm", "intentId": "3ba08600fb034e238c781ccf952a61a4", "lastModified": "2026-08-26T12:23:38+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "f7d2aee0bcf1396cd8ab3b1064b6a032eccc04f2d655a336023e13528574903d", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.895216+00:00", "framework": "vllm", "intentId": "00b624f4c6844926865cc89ae3c469ee", "lastModified": "2026-08-26T18:16:42+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B-IT-Research", "repoId": "aisingapore/SEA-LION-v1-7B-IT-Research", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 2048, "tensorParallel": 1}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.895272+00:00", "framework": "vllm", "intentId": "6b550b2018c74d289e6faf85cede4a41", "lastModified": "2026-08-24T20:38:11+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-quantized.w8a16", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.895328+00:00", "framework": "vllm", "intentId": "b9b8fdd4c4914bf493b47f141f258f88", "lastModified": "2026-09-08T13:43:47+00:00", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "repoId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.895385+00:00", "framework": "vllm", "intentId": "89975052394c4c2fa9f0fadc2c14bb06", "lastModified": "2026-08-26T14:51:55+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B-IT-GPTQ", "repoId": "aisingapore/SEA-LION-v1-7B-IT-GPTQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.895440+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1b0deeaf714048619ec694300ae7132f", "lastModified": "2026-09-12T12:30:14+00:00", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-MLX", "repoId": "OpenBMB/MiniCPM5-2B-MLX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.895484+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c5fd10f6c37b4e8ab55bae0188ba35f4", "lastModified": "2026-08-24T20:33:29+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-3b-FP8", "repoId": "RedHatAI/starcoder2-3b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.895529+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0acef89251224a6c812b22e9cda06d11", "lastModified": "2026-09-03T18:32:29+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Apodex-1.1-mini-AWQ-INT4", "repoId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.895574+00:00", "framework": "vllm_fix_tokenizer", "intentId": "86657f83311642d4949011fc0f497db3", "lastModified": "2026-09-09T06:31:08+00:00", "modelAddress": "https://modelscope.cn/models/ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "repoId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.895617+00:00", "framework": "vllm_fix_tokenizer", "intentId": "aee324df075745b5a4efa959d3c04786", "lastModified": "2026-09-09T06:27:24+00:00", "modelAddress": "https://modelscope.cn/models/ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "repoId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.895661+00:00", "framework": "vllm_fix_tokenizer", "intentId": "11b67ad669e742fcb006ac933f789124", "lastModified": "2026-08-28T05:30:04+00:00", "modelAddress": "https://modelscope.cn/models/whcl412/mlx-LycheeAI-coder-1.7b", "repoId": "whcl412/mlx-LycheeAI-coder-1.7b", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.895710+00:00", "framework": "vllm_fix_tokenizer", "intentId": "3cf6f0f054e64f139edcbeefd8ef6c41", "lastModified": "2026-08-26T19:32:38+00:00", "modelAddress": "https://modelscope.cn/models/pfnet/plamo-3-nict-8b-base", "repoId": "pfnet/plamo-3-nict-8b-base", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.895754+00:00", "framework": "transformers", "intentId": "52c2e40370fb4df2aa0374bb8934c0b9", "lastModified": "2026-08-24T22:55:11+00:00", "modelAddress": "https://modelscope.cn/models/BAAI/AquilaMed-RL", "repoId": "BAAI/AquilaMed-RL", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.895818+00:00", "framework": "transformers", "intentId": "be9ee69e52874b809a9b2d66b62777aa", "lastModified": "2026-09-08T03:51:51+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B", "repoId": "XHToken/Spark-X2.5-4B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.895881+00:00", "framework": "transformers", "intentId": "fe4feaf166574d7b933ad4ea891df18c", "lastModified": "2026-09-03T13:37:32+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-1.7B", "repoId": "XHToken/Spark-X2.5-1.7B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.895944+00:00", "framework": "transformers", "intentId": "2fc1e97125b949a094e9b517d7505f20", "lastModified": "2026-08-26T16:41:11+00:00", "modelAddress": "https://modelscope.cn/models/apodex/Apodex-1.1-mini-GPTQ-Int4", "repoId": "apodex/Apodex-1.1-mini-GPTQ-Int4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.896007+00:00", "framework": "transformers", "intentId": "73d35abf866a46458aec9cb7a38611ef", "lastModified": "2026-08-26T17:23:58+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.896070+00:00", "framework": "transformers", "intentId": "90f9d1c2fa8343f59442bee699f9de9a", "lastModified": "2026-08-26T17:20:09+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.896132+00:00", "framework": "transformers", "intentId": "54a41138a0564f5b8dc214031dcc800b", "lastModified": "2026-08-26T20:28:29+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.896194+00:00", "framework": "transformers", "intentId": "4f2ee2cedfe444daa826a65b9f4e3538", "lastModified": "2026-09-01T03:52:21+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "repoId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.896256+00:00", "framework": "transformers", "intentId": "0db77c4ffbfe4975843be3f7db424e19", "lastModified": "2026-09-02T05:56:49+00:00", "modelAddress": "https://modelscope.cn/models/Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "repoId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.896319+00:00", "framework": "transformers", "intentId": "74fec891dd8844a2ac0f78a85e663421", "lastModified": "2026-08-28T09:38:42+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "repoId": "mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.896381+00:00", "framework": "transformers", "intentId": "a1f732b0d57145b5b93c32593bdba261", "lastModified": "2026-09-08T15:45:26+00:00", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/AppleScript-8B-JANG_4M", "repoId": "JANGQ-AI/AppleScript-8B-JANG_4M", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.896443+00:00", "framework": "transformers", "intentId": "36f2d3cf99b2444baf39aada6ac4a195", "lastModified": "2026-08-29T01:07:23+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "repoId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.896505+00:00", "framework": "transformers", "intentId": "c589c3b7d7084349b4624132f42f5ad2", "lastModified": "2026-09-03T07:00:50+00:00", "modelAddress": "https://modelscope.cn/models/EschaLabs/Qwen3.8-27B-Escha-W2", "repoId": "EschaLabs/Qwen3.8-27B-Escha-W2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.896567+00:00", "framework": "transformers", "intentId": "c98b96618fdb46cb9bc70134746d1cd6", "lastModified": "2026-08-26T12:21:34+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.896628+00:00", "framework": "vllm-patch-tokenizer", "intentId": "a65a124a0a32414caf0f465486bc65bb", "lastModified": "2026-08-24T20:25:10+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-quantized.w8a16", "repoId": "neuralmagic/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.896676+00:00", "framework": "vllm-patch-tokenizer", "intentId": "5ba226424f164ed8bc97525a66451828", "lastModified": "2026-08-24T20:22:00+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-it-quantized.w8a16", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.896719+00:00", "framework": "vllm-patch-tokenizer", "intentId": "a4c984a30e024bc6b6f45dd899cca756", "lastModified": "2026-08-24T20:10:58+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.896769+00:00", "framework": "vllm-patch-tokenizer", "intentId": "361c8b511e7d47939d7f479fe10a9eb0", "lastModified": "2026-08-24T20:22:06+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-quantized.w8a16", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.896835+00:00", "framework": "vllm-patch-tokenizer", "intentId": "8c7e39fde75744f68e5c0ba1253f037b", "lastModified": "2026-08-24T20:14:53+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-9b-it-quantized.w4a16", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.896878+00:00", "framework": "vllm-patch-tokenizer", "intentId": "43db9dc4e7614f6bad6290bdf3470695", "lastModified": "2026-08-24T20:21:52+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-7b-quantized.w8a16", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.896920+00:00", "framework": "vllm-patch-tokenizer", "intentId": "d3a5ccee060f4e79894ac32884971fe2", "lastModified": "2026-08-24T19:53:24+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "repoId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.896963+00:00", "framework": "vllm-patch-tokenizer", "intentId": "5c720f007a8448849384ca38651d483f", "lastModified": "2026-08-24T20:30:03+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-quantized.w4a16", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.897005+00:00", "framework": "vllm-patch-tokenizer", "intentId": "d575710974bf47ae811c4fd08a1d81d2", "lastModified": "2026-08-24T20:23:31+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Qwen2-1.5B-Instruct-quantized.w8a8", "repoId": "RedHatAI/Qwen2-1.5B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.897048+00:00", "framework": "vllm-patch-tokenizer", "intentId": "8ce8288dc59a4ad08a2855cb7ddd6203", "lastModified": "2026-08-24T20:36:33+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.897090+00:00", "framework": "vllm-patch-tokenizer", "intentId": "a5679e98e24b4a7daf16c16f1f36ce9a", "lastModified": "2026-08-24T20:20:16+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-FP8", "repoId": "RedHatAI/starcoder2-15b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.897133+00:00", "framework": "vllm-patch-tokenizer", "intentId": "fde8444c53024d38af6f1afb57a988af", "lastModified": "2026-08-24T20:18:47+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-27b-it-quantized.w8a16", "repoId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.897176+00:00", "framework": "vllm-patch-tokenizer", "intentId": "43027ae4d89b444889d4544ada63d22b", "lastModified": "2026-08-24T22:06:31+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-FP8", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.897218+00:00", "framework": "vllm-patch-tokenizer", "intentId": "c988277c3300447f80cb405c03d184b2", "lastModified": "2026-08-26T16:45:23+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "repoId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.897260+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f172acc9110c4b9780c7bbf22deb28d5", "lastModified": "2026-08-26T20:08:57+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.897303+00:00", "framework": "vllm_tokenizer_patch", "intentId": "608c2c53e9f54306bdfbbee5b1b2e080", "lastModified": "2026-08-24T20:36:29+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "e47a3c32464a4e699031e56f23292dcf", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:10:30.897344+00:00", "framework": "vllm_tokenizer_patch", "intentId": "736c3b51beee4235aa8d2e58803951ab", "lastModified": "2026-08-26T16:48:25+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B-IT", "repoId": "aisingapore/SEA-LION-v1-7B-IT", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "b37382fdd745426db7b1ad8215597fa9", "completedAt": "2026-09-20T09:09:02.433172+00:00", "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:07:27.652424+00:00", "framework": "vllm", "intentId": "fd895c19603a4722bbcc3c61b7f9b80c", "repoId": "bharatgenai/Param2-17B-A2.4B-Thinking", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "b37382fdd745426db7b1ad8215597fa9", "completedAt": "2026-09-20T09:09:02.433169+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:07:27.652365+00:00", "framework": "vllm-customized", "intentId": "7de37ff44c8c44c2b22cae69a63eed68", "repoId": "XHToken/Spark-X2.5-4B-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "b37382fdd745426db7b1ad8215597fa9", "completedAt": "2026-09-20T09:09:02.433166+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:07:27.652306+00:00", "framework": "vllm-customized", "intentId": "b54e168b3db34ec49330de7a2f5256d2", "repoId": "TokenRhythm/NeoHorse-1-9B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}