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

state: generation 11602 (result)

Browse Source
This commit is contained in:
CoolBoy
2026-09-21 18:32:47 +00:00
parent 425466bc2b
commit 9d9e980ca6
5 changed files with 100 additions and 127 deletions
Download Patch File Download Diff File Expand all files Collapse all files

171
.modelhub_state/recovery_intents.jsonl
View File

@@ -2202,67 +2202,67 @@
{"batchId": "7af9554b5bf5474487f4f82ccb9bf547", "completedAt": "2026-09-21T18:17:49.896447+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:13:41.099153+00:00", "framework": "transformers", "intentId": "52442a3098a44ab285d8a15ad63abe46", "lastModified": "2026-08-24T20:29:58+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-quantized.w8a16", "reason": null, "reconciledAt": "2026-09-21T18:17:52.253626+00:00", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Iluvatar_bi-150", "taskId": "5005304", "taskType": "text-generation"} {"batchId": "7af9554b5bf5474487f4f82ccb9bf547", "completedAt": "2026-09-21T18:17:49.896447+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:13:41.099153+00:00", "framework": "transformers", "intentId": "52442a3098a44ab285d8a15ad63abe46", "lastModified": "2026-08-24T20:29:58+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-quantized.w8a16", "reason": null, "reconciledAt": "2026-09-21T18:17:52.253626+00:00", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Iluvatar_bi-150", "taskId": "5005304", "taskType": "text-generation"}
{"batchId": "7af9554b5bf5474487f4f82ccb9bf547", "completedAt": "2026-09-21T18:17:49.896472+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:13:41.099779+00:00", "framework": "vllm_tokenizer_patch", "intentId": "95830cb365a34d19a012a90408099cac", "lastModified": "2026-08-26T12:24:21+00:00", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "reason": null, "reconciledAt": "2026-09-21T18:17:52.254056+00:00", "repoId": "ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Iluvatar_bi-150", "taskId": "5005325", "taskType": "text-generation"} {"batchId": "7af9554b5bf5474487f4f82ccb9bf547", "completedAt": "2026-09-21T18:17:49.896472+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:13:41.099779+00:00", "framework": "vllm_tokenizer_patch", "intentId": "95830cb365a34d19a012a90408099cac", "lastModified": "2026-08-26T12:24:21+00:00", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "reason": null, "reconciledAt": "2026-09-21T18:17:52.254056+00:00", "repoId": "ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Iluvatar_bi-150", "taskId": "5005325", "taskType": "text-generation"}
{"batchId": "7af9554b5bf5474487f4f82ccb9bf547", "completedAt": "2026-09-21T18:17:49.896475+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:13:41.099822+00:00", "framework": "vllm_tokenizer_patch", "intentId": "9e31ef1375074f6a9e31138e444449e7", "lastModified": "2026-08-26T12:23:32+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "reason": null, "reconciledAt": "2026-09-21T18:17:52.252995+00:00", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Iluvatar_bi-150", "taskId": "5005326", "taskType": "text-generation"} {"batchId": "7af9554b5bf5474487f4f82ccb9bf547", "completedAt": "2026-09-21T18:17:49.896475+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:13:41.099822+00:00", "framework": "vllm_tokenizer_patch", "intentId": "9e31ef1375074f6a9e31138e444449e7", "lastModified": "2026-08-26T12:23:32+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "reason": null, "reconciledAt": "2026-09-21T18:17:52.252995+00:00", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Iluvatar_bi-150", "taskId": "5005326", "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.189980+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a0fc716eed5d4cd187add7c2b1105d1f", "lastModified": "2026-08-24T14:38:54+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-Non-Uniform-compressed-tensors", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-Non-Uniform-compressed-tensors", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226485+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.189980+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a0fc716eed5d4cd187add7c2b1105d1f", "lastModified": "2026-08-24T14:38:54+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-Non-Uniform-compressed-tensors", "reason": null, "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-Non-Uniform-compressed-tensors", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "5005405", "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.190109+00:00", "framework": "vllm_tokenizer_patch", "intentId": "b71ab6f5cb2747bb8ca56c2ee36dab7b", "lastModified": "2026-08-24T15:42:55+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8-channel-a8-tensor", "repoId": "nm-testing/tinyllama-oneshot-w8-channel-a8-tensor", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226504+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.190109+00:00", "framework": "vllm_tokenizer_patch", "intentId": "b71ab6f5cb2747bb8ca56c2ee36dab7b", "lastModified": "2026-08-24T15:42:55+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8-channel-a8-tensor", "reason": null, "repoId": "nm-testing/tinyllama-oneshot-w8-channel-a8-tensor", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "5005404", "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.190163+00:00", "framework": "vllm_tokenizer_patch", "intentId": "28c8984381d7423b812e99045958e428", "lastModified": "2026-08-24T17:35:14+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-llama3-8b-Instruct-SmoothQuant-Fp8", "repoId": "nm-testing/Meta-llama3-8b-Instruct-SmoothQuant-Fp8", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226508+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.190163+00:00", "framework": "vllm_tokenizer_patch", "intentId": "28c8984381d7423b812e99045958e428", "lastModified": "2026-08-24T17:35:14+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-llama3-8b-Instruct-SmoothQuant-Fp8", "reason": null, "repoId": "nm-testing/Meta-llama3-8b-Instruct-SmoothQuant-Fp8", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "5005403", "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.190214+00:00", "framework": "vllm_tokenizer_patch", "intentId": "da3ee6b16b8641588c6596d80fe2b095", "lastModified": "2026-08-24T17:33:00+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test-bos", "repoId": "nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test-bos", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226527+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.190396+00:00", "framework": "vllm_fix_tokenizer", "intentId": "85263c16823c403abbd09d4e45a054ee", "lastModified": "2026-08-24T16:38:03+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t", "reason": null, "repoId": "nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "5005406", "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.190265+00:00", "framework": "vllm_fix_tokenizer", "intentId": "71396eb8748a4fb2b0249b6888336fba", "lastModified": "2026-08-24T15:14:56+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/SmolLM-135M-Instruct-quantized.w4a16", "repoId": "nm-testing/SmolLM-135M-Instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226539+00:00", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.190568+00:00", "framework": "vllm_fix_tokenizer", "intentId": "66f81a17b3a542f59dc22c5cd8a242cf", "lastModified": "2026-08-24T16:10:08+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w4a16-channel-v2", "reason": null, "repoId": "nm-testing/tinyllama-oneshot-w4a16-channel-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "5005433", "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.190309+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ec1da6cc23b842249b6f6d176f252d8a", "lastModified": "2026-08-24T17:58:05+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-one-shot-w4a16-group-packed", "repoId": "nm-testing/tinyllama-one-shot-w4a16-group-packed", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226572+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.191103+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4f6c42a436c345878534501f24e3d607", "lastModified": "2026-08-24T18:26:59+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/nonuniform", "reason": null, "repoId": "nm-testing/nonuniform", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "5005434", "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.190353+00:00", "framework": "vllm_fix_tokenizer", "intentId": "362e11d9eaed4f55a8e6b9f6a41bdc0b", "lastModified": "2026-08-24T16:17:12+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8a8-channel-dynamic-token-v2", "repoId": "nm-testing/tinyllama-oneshot-w8a8-channel-dynamic-token-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226574+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.191154+00:00", "framework": "vllm_tokenizer_patch", "intentId": "9faa958f2e79486fa3ab3c0e8296ab27", "lastModified": "2026-08-24T20:08:44+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "reason": null, "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "5005435", "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.190396+00:00", "framework": "vllm_fix_tokenizer", "intentId": "85263c16823c403abbd09d4e45a054ee", "lastModified": "2026-08-24T16:38:03+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t", "repoId": "nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226577+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.191204+00:00", "framework": "vllm_tokenizer_patch", "intentId": "3ba9b91b71b444958bc39bb0271eaddb", "lastModified": "2026-08-24T19:59:13+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-FP8", "reason": null, "repoId": "RedHatAI/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "5005436", "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.190439+00:00", "framework": "vllm_fix_tokenizer", "intentId": "253002042a844710a4f853e065b07c24", "lastModified": "2026-08-24T17:41:35+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test", "repoId": "nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226579+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.191253+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6929e3cb3b0147b4807a8993ae3bd21d", "lastModified": "2026-08-24T19:36:07+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w4a16", "reason": null, "repoId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "5005437", "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.190482+00:00", "framework": "vllm_fix_tokenizer", "intentId": "af1c262be56e4ae09285ddc9ef79fb56", "lastModified": "2026-08-24T14:45:05+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-W4-Group128-A16-Test", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W4-Group128-A16-Test", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226582+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.191301+00:00", "framework": "vllm_tokenizer_patch", "intentId": "26a3be8be35644fcbfc91d6b7019ef94", "lastModified": "2026-09-11T15:37:46+00:00", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-base-32K", "reason": null, "repoId": "CohereLabs/tiny-aya-base-32K", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "5005438", "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.190525+00:00", "framework": "vllm_fix_tokenizer", "intentId": "9d0d3accf8ba4e069a9dc913e6092e81", "lastModified": "2026-08-24T15:48:56+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2-asym", "repoId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2-asym", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226584+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.191349+00:00", "framework": "vllm", "intentId": "49cbea0b76b9427688f32a3f2eb3a963", "lastModified": "2026-08-24T20:22:22+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "reason": null, "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "5005439", "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.190568+00:00", "framework": "vllm_fix_tokenizer", "intentId": "66f81a17b3a542f59dc22c5cd8a242cf", "lastModified": "2026-08-24T16:10:08+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w4a16-channel-v2", "repoId": "nm-testing/tinyllama-oneshot-w4a16-channel-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226586+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.191407+00:00", "framework": "vllm", "intentId": "dae8a67cd520484494f9358ff065428b", "lastModified": "2026-08-26T14:51:55+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B-IT-GPTQ", "reason": null, "repoId": "aisingapore/SEA-LION-v1-7B-IT-GPTQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "5005440", "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.190610+00:00", "framework": "vllm_fix_tokenizer", "intentId": "bc036d72597a49cab90280c1053bc8f5", "lastModified": "2026-08-24T15:07:56+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Qwen2-1.5B-Instruct-FP8W8", "repoId": "nm-testing/Qwen2-1.5B-Instruct-FP8W8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226682+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.192829+00:00", "framework": "transformers", "intentId": "55eaf8fb116c40f5b9b08fb04d4d9d80", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.190653+00:00", "framework": "vllm_fix_tokenizer", "intentId": "9a61171dde534ec8a32bf2cb31e00275", "lastModified": "2026-08-24T19:10:38+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "repoId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226680+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.192769+00:00", "framework": "transformers", "intentId": "a6e0ce9b54734dc3acaa664c69592420", "repoId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.190718+00:00", "framework": "vllm_tokenizer_patch", "intentId": "663e4bd6919847dc900e22429fc0e59b", "lastModified": "2026-08-24T16:03:28+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/llama3-8b-w8_channel-a8_tensor-compressed", "repoId": "nm-testing/llama3-8b-w8_channel-a8_tensor-compressed", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226677+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.192708+00:00", "framework": "transformers", "intentId": "e96c0c52b21d436f8b2b6bad32a1b5d0", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.190759+00:00", "framework": "vllm_tokenizer_patch", "intentId": "efcf4496380140cf8bbe3f5d4863a9c8", "lastModified": "2026-08-24T16:35:49+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-test", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-test", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226674+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.192642+00:00", "framework": "transformers", "intentId": "82807abbc0494464a7084f09a893a55a", "repoId": "neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.190797+00:00", "framework": "vllm_tokenizer_patch", "intentId": "b9c85735dd0e44cdb871b447dc0cc295", "lastModified": "2026-08-24T14:42:46+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-W4A16-ACTORDER-compressed-tensors-test", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-ACTORDER-compressed-tensors-test", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226661+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.192580+00:00", "framework": "transformers", "intentId": "f8a022ae5bbc4b068e5b0297192bf8a7", "repoId": "BAAI/AquilaMed-RL", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "duplicate", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.190834+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e1d035fc9e224bbd8c9658f2e8977f7b", "lastModified": "2026-08-24T16:01:21+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w4a16-group128-v2", "repoId": "nm-testing/tinyllama-oneshot-w4a16-group128-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226657+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.192538+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6faedc357eea48b1b1621b677148ae7b", "repoId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "duplicate", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.190872+00:00", "framework": "vllm_tokenizer_patch", "intentId": "fa0c131bf2fa4e04ac6ca8e71841fa48", "lastModified": "2026-08-24T17:49:53+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-nonuniform-test", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-nonuniform-test", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226655+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.192495+00:00", "framework": "vllm_fix_tokenizer", "intentId": "38438f40ce7a4b229e40f7782affc10d", "repoId": "pfnet/plamo-3-nict-8b-base", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.190910+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f58b7011036f4f48abff229ce866b609", "lastModified": "2026-08-24T16:40:22+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226652+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.192454+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ef43ef8bf5054b41b4259735f7224a40", "repoId": "whcl412/mlx-LycheeAI-coder-1.7b", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.190947+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1af6b1754cc8479683f46d56fbaf1ee3", "lastModified": "2026-08-24T17:53:32+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-llama3-8b-Instruct-quant-FP8", "repoId": "nm-testing/Meta-llama3-8b-Instruct-quant-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226649+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.192411+00:00", "framework": "vllm_fix_tokenizer", "intentId": "30c11b30dd9241abb16024cd23df37e2", "repoId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.190985+00:00", "framework": "vllm-mlu", "intentId": "3c63dd60f8e44a76b7329add467ec905", "lastModified": "2026-08-24T19:21:33+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-quantized.w8a8", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226647+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.192369+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6b161b30eead49d190e28ec4cf2c4ec8", "repoId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.191052+00:00", "framework": "vllm_tokenizer_patch", "intentId": "17f7cb4634cf48c5ba8275fe44ec0275", "lastModified": "2026-08-24T18:12:10+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226644+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.192327+00:00", "framework": "vllm_fix_tokenizer", "intentId": "09929b0e985d4b449d0e612c6abe1346", "repoId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.191103+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4f6c42a436c345878534501f24e3d607", "lastModified": "2026-08-24T18:26:59+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/nonuniform", "repoId": "nm-testing/nonuniform", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226641+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.192283+00:00", "framework": "vllm_fix_tokenizer", "intentId": "10845c6842124241b04c8d7245ce89a2", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.191154+00:00", "framework": "vllm_tokenizer_patch", "intentId": "9faa958f2e79486fa3ab3c0e8296ab27", "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": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226639+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.192241+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b224fcad85d94a53bd04ce41c007742a", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.191204+00:00", "framework": "vllm_tokenizer_patch", "intentId": "3ba9b91b71b444958bc39bb0271eaddb", "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, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226637+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.192198+00:00", "framework": "vllm_fix_tokenizer", "intentId": "28d344632e0145d8b35adcc75c5eb4ec", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.191253+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6929e3cb3b0147b4807a8993ae3bd21d", "lastModified": "2026-08-24T19:36:07+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w4a16", "repoId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226634+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.192156+00:00", "framework": "vllm_fix_tokenizer", "intentId": "cbed86fceefe411cb8b651dc6c8c379f", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.191301+00:00", "framework": "vllm_tokenizer_patch", "intentId": "26a3be8be35644fcbfc91d6b7019ef94", "lastModified": "2026-09-11T15:37:46+00:00", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-base-32K", "repoId": "CohereLabs/tiny-aya-base-32K", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226631+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.192114+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d3383e8e70314e5d8c81411b1ba321ea", "repoId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "duplicate", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.191349+00:00", "framework": "vllm", "intentId": "49cbea0b76b9427688f32a3f2eb3a963", "lastModified": "2026-08-24T20:22:22+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226628+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.192072+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5381a9fee8a249fd96df71d653a791b8", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.191407+00:00", "framework": "vllm", "intentId": "dae8a67cd520484494f9358ff065428b", "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": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226625+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.192030+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5e1048caf6c44f11b3f7c3197a1cbd5b", "repoId": "nm-testing/Meta-Llama-3.1-8B-Instruct-FP8-hf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.191464+00:00", "framework": "vllm_fix_tokenizer", "intentId": "36c9b8798a4f415780562682e7f09e27", "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": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226622+00:00", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.191988+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6e3c281eb32c45b99acddd7a7770f66c", "repoId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.191507+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2d0719467d694011af15d76954155b81", "lastModified": "2026-08-24T19:34:25+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226619+00:00", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.191945+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e50e03c984a94ec88b897b052244614a", "repoId": "nm-testing/tinyllama-marlin24-w4a16-group128", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.191550+00:00", "framework": "vllm_fix_tokenizer", "intentId": "39d641c245364b78b7bef5c5880b503b", "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": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226617+00:00", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.191902+00:00", "framework": "vllm_fix_tokenizer", "intentId": "810c4e19c40d4c2cae5ea8c3cfda6916", "repoId": "nm-testing/tinyllama-oneshot-w8a8-static-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.191593+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b7f298b4e69247c192af7b5a23b2c8b9", "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": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226615+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.191860+00:00", "framework": "vllm_fix_tokenizer", "intentId": "68109039a56d4c52b88cf5e601ffaa46", "repoId": "nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t-alt", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.191636+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d2e06734ea304f54b588346894f54fe2", "lastModified": "2026-08-24T19:39:21+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-9b-it-quantized.w8a16", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226612+00:00", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.191816+00:00", "framework": "vllm_fix_tokenizer", "intentId": "15850e66185f4c62a319ca0a6a4d856b", "repoId": "nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.191689+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a25af3a157c44970b73ad0117bf69a90", "lastModified": "2026-08-24T19:42:52+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-7b-FP8", "repoId": "neuralmagic/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226609+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.191774+00:00", "framework": "vllm_fix_tokenizer", "intentId": "10b2b731c12248a29bcc7b3866d86eff", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.191731+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b32fb26c6bcf468a95aba942e25a8429", "lastModified": "2026-08-24T19:39:20+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-quantized.w8a16", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226606+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.191731+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b32fb26c6bcf468a95aba942e25a8429", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.191774+00:00", "framework": "vllm_fix_tokenizer", "intentId": "10b2b731c12248a29bcc7b3866d86eff", "lastModified": "2026-08-24T19:26:17+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-it-quantized.w4a16", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226603+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.191689+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a25af3a157c44970b73ad0117bf69a90", "repoId": "neuralmagic/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.191816+00:00", "framework": "vllm_fix_tokenizer", "intentId": "15850e66185f4c62a319ca0a6a4d856b", "lastModified": "2026-08-24T18:09:20+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change", "repoId": "nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226601+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.191636+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d2e06734ea304f54b588346894f54fe2", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.191860+00:00", "framework": "vllm_fix_tokenizer", "intentId": "68109039a56d4c52b88cf5e601ffaa46", "lastModified": "2026-08-24T17:02:50+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t-alt", "repoId": "nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t-alt", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226598+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.191593+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b7f298b4e69247c192af7b5a23b2c8b9", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.191902+00:00", "framework": "vllm_fix_tokenizer", "intentId": "810c4e19c40d4c2cae5ea8c3cfda6916", "lastModified": "2026-08-24T18:26:39+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8a8-static-v2", "repoId": "nm-testing/tinyllama-oneshot-w8a8-static-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226595+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.191550+00:00", "framework": "vllm_fix_tokenizer", "intentId": "39d641c245364b78b7bef5c5880b503b", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.191945+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e50e03c984a94ec88b897b052244614a", "lastModified": "2026-08-24T18:28:40+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-marlin24-w4a16-group128", "repoId": "nm-testing/tinyllama-marlin24-w4a16-group128", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226592+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.191507+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2d0719467d694011af15d76954155b81", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.191988+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6e3c281eb32c45b99acddd7a7770f66c", "lastModified": "2026-08-24T18:24:11+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2", "repoId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226589+00:00", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.191464+00:00", "framework": "vllm_fix_tokenizer", "intentId": "36c9b8798a4f415780562682e7f09e27", "repoId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.192030+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5e1048caf6c44f11b3f7c3197a1cbd5b", "lastModified": "2026-08-24T18:06:52+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3.1-8B-Instruct-FP8-hf", "repoId": "nm-testing/Meta-Llama-3.1-8B-Instruct-FP8-hf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226570+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.191052+00:00", "framework": "vllm_tokenizer_patch", "intentId": "17f7cb4634cf48c5ba8275fe44ec0275", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.192072+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5381a9fee8a249fd96df71d653a791b8", "lastModified": "2026-08-24T19:39:28+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-3b-quantized.w8a16", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226568+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.190985+00:00", "framework": "vllm-mlu", "intentId": "3c63dd60f8e44a76b7329add467ec905", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.192114+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d3383e8e70314e5d8c81411b1ba321ea", "lastModified": "2026-08-24T19:51:52+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "repoId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226564+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.190947+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1af6b1754cc8479683f46d56fbaf1ee3", "repoId": "nm-testing/Meta-llama3-8b-Instruct-quant-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.192156+00:00", "framework": "vllm_fix_tokenizer", "intentId": "cbed86fceefe411cb8b651dc6c8c379f", "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": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226561+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.190910+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f58b7011036f4f48abff229ce866b609", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.192198+00:00", "framework": "vllm_fix_tokenizer", "intentId": "28d344632e0145d8b35adcc75c5eb4ec", "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": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226558+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.190872+00:00", "framework": "vllm_tokenizer_patch", "intentId": "fa0c131bf2fa4e04ac6ca8e71841fa48", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-nonuniform-test", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.192241+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b224fcad85d94a53bd04ce41c007742a", "lastModified": "2026-08-24T20:26:53+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-9b-it-quantized.w8a16", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226555+00:00", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.190834+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e1d035fc9e224bbd8c9658f2e8977f7b", "repoId": "nm-testing/tinyllama-oneshot-w4a16-group128-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.192283+00:00", "framework": "vllm_fix_tokenizer", "intentId": "10845c6842124241b04c8d7245ce89a2", "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": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226553+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.190797+00:00", "framework": "vllm_tokenizer_patch", "intentId": "b9c85735dd0e44cdb871b447dc0cc295", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-ACTORDER-compressed-tensors-test", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.192327+00:00", "framework": "vllm_fix_tokenizer", "intentId": "09929b0e985d4b449d0e612c6abe1346", "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": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226550+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.190759+00:00", "framework": "vllm_tokenizer_patch", "intentId": "efcf4496380140cf8bbe3f5d4863a9c8", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-test", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.192369+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6b161b30eead49d190e28ec4cf2c4ec8", "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": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226547+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.190718+00:00", "framework": "vllm_tokenizer_patch", "intentId": "663e4bd6919847dc900e22429fc0e59b", "repoId": "nm-testing/llama3-8b-w8_channel-a8_tensor-compressed", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.192411+00:00", "framework": "vllm_fix_tokenizer", "intentId": "30c11b30dd9241abb16024cd23df37e2", "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": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226544+00:00", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.190653+00:00", "framework": "vllm_fix_tokenizer", "intentId": "9a61171dde534ec8a32bf2cb31e00275", "repoId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.192454+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ef43ef8bf5054b41b4259735f7224a40", "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": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226542+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.190610+00:00", "framework": "vllm_fix_tokenizer", "intentId": "bc036d72597a49cab90280c1053bc8f5", "repoId": "nm-testing/Qwen2-1.5B-Instruct-FP8W8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.192495+00:00", "framework": "vllm_fix_tokenizer", "intentId": "38438f40ce7a4b229e40f7782affc10d", "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": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226536+00:00", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.190525+00:00", "framework": "vllm_fix_tokenizer", "intentId": "9d0d3accf8ba4e069a9dc913e6092e81", "repoId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2-asym", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.192538+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6faedc357eea48b1b1621b677148ae7b", "lastModified": "2026-09-09T06:50:48+00:00", "modelAddress": "https://modelscope.cn/models/ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "repoId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226533+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.190482+00:00", "framework": "vllm_fix_tokenizer", "intentId": "af1c262be56e4ae09285ddc9ef79fb56", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W4-Group128-A16-Test", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.192580+00:00", "framework": "transformers", "intentId": "f8a022ae5bbc4b068e5b0297192bf8a7", "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": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226530+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.190439+00:00", "framework": "vllm_fix_tokenizer", "intentId": "253002042a844710a4f853e065b07c24", "repoId": "nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.192642+00:00", "framework": "transformers", "intentId": "82807abbc0494464a7084f09a893a55a", "lastModified": "2026-08-24T19:53:06+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "repoId": "neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226524+00:00", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.190353+00:00", "framework": "vllm_fix_tokenizer", "intentId": "362e11d9eaed4f55a8e6b9f6a41bdc0b", "repoId": "nm-testing/tinyllama-oneshot-w8a8-channel-dynamic-token-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.192708+00:00", "framework": "transformers", "intentId": "e96c0c52b21d436f8b2b6bad32a1b5d0", "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": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226521+00:00", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.190309+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ec1da6cc23b842249b6f6d176f252d8a", "repoId": "nm-testing/tinyllama-one-shot-w4a16-group-packed", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.192769+00:00", "framework": "transformers", "intentId": "a6e0ce9b54734dc3acaa664c69592420", "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": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226518+00:00", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.190265+00:00", "framework": "vllm_fix_tokenizer", "intentId": "71396eb8748a4fb2b0249b6888336fba", "repoId": "nm-testing/SmolLM-135M-Instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "1fb2a68ee155485c8988534b790a9dd2", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.192829+00:00", "framework": "transformers", "intentId": "55eaf8fb116c40f5b9b08fb04d4d9d80", "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": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "1fb2a68ee155485c8988534b790a9dd2", "completedAt": "2026-09-21T18:32:47.226511+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:22:37.190214+00:00", "framework": "vllm_tokenizer_patch", "intentId": "da3ee6b16b8641588c6596d80fe2b095", "repoId": "nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test-bos", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "7af9554b5bf5474487f4f82ccb9bf547", "completedAt": "2026-09-21T18:17:49.896489+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:13:41.100062+00:00", "framework": "vllm", "intentId": "3975ec14f6834bde9a242b9ba52ddc70", "repoId": "nm-testing/llama-3-instruct-w8a8-dyn-per-token-test", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"} {"batchId": "7af9554b5bf5474487f4f82ccb9bf547", "completedAt": "2026-09-21T18:17:49.896489+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:13:41.100062+00:00", "framework": "vllm", "intentId": "3975ec14f6834bde9a242b9ba52ddc70", "repoId": "nm-testing/llama-3-instruct-w8a8-dyn-per-token-test", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"}
{"batchId": "7af9554b5bf5474487f4f82ccb9bf547", "completedAt": "2026-09-21T18:17:49.896487+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:13:41.100003+00:00", "framework": "vllm", "intentId": "d481d34a389b406d98c18aa1eacb60a2", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Per-Token-Test", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"} {"batchId": "7af9554b5bf5474487f4f82ccb9bf547", "completedAt": "2026-09-21T18:17:49.896487+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:13:41.100003+00:00", "framework": "vllm", "intentId": "d481d34a389b406d98c18aa1eacb60a2", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Per-Token-Test", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"}
{"batchId": "7af9554b5bf5474487f4f82ccb9bf547", "completedAt": "2026-09-21T18:17:49.896484+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:13:41.099943+00:00", "framework": "vllm", "intentId": "80947b4a8b704dcd9ec2ed480f63f2c8", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"} {"batchId": "7af9554b5bf5474487f4f82ccb9bf547", "completedAt": "2026-09-21T18:17:49.896484+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:13:41.099943+00:00", "framework": "vllm", "intentId": "80947b4a8b704dcd9ec2ed480f63f2c8", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"}
@@ -2514,52 +2514,3 @@
{"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427631+00:00", "configFingerprint": "f49713b9fe8e3e7683ab2722544c85a44993bcd72b9421c1599f634e68b3a2f7", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.706139+00:00", "framework": "vllm", "intentId": "935f73d13426414ea23df8acf6c28c5c", "repoId": "nm-testing/tinyllama-marlin24-w4a16-group128", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} {"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427631+00:00", "configFingerprint": "f49713b9fe8e3e7683ab2722544c85a44993bcd72b9421c1599f634e68b3a2f7", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.706139+00:00", "framework": "vllm", "intentId": "935f73d13426414ea23df8acf6c28c5c", "repoId": "nm-testing/tinyllama-marlin24-w4a16-group128", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
{"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427628+00:00", "configFingerprint": "f49713b9fe8e3e7683ab2722544c85a44993bcd72b9421c1599f634e68b3a2f7", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.706092+00:00", "framework": "vllm", "intentId": "74a5c4c55a374e9985272711c3927ffc", "repoId": "nm-testing/tinyllama-oneshot-w8a8-static-v2", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} {"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427628+00:00", "configFingerprint": "f49713b9fe8e3e7683ab2722544c85a44993bcd72b9421c1599f634e68b3a2f7", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.706092+00:00", "framework": "vllm", "intentId": "74a5c4c55a374e9985272711c3927ffc", "repoId": "nm-testing/tinyllama-oneshot-w8a8-static-v2", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
{"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427626+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.706045+00:00", "framework": "vllm", "intentId": "f4f9c850ca7c419da19cd7d1adc4511f", "repoId": "neuralmagic/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} {"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427626+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.706045+00:00", "framework": "vllm", "intentId": "f4f9c850ca7c419da19cd7d1adc4511f", "repoId": "neuralmagic/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
{"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427622+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.705998+00:00", "framework": "vllm", "intentId": "251793cebe9c436e9978003e3e0f51b6", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
{"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427617+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.705914+00:00", "framework": "vllm-patch-tokenizer", "intentId": "b1f98cc5ed8146408515dd4732d87fb0", "repoId": "RedHatAI/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427614+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.705873+00:00", "framework": "vllm-patch-tokenizer", "intentId": "9171f929a96e41a7b441bf963238c635", "repoId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427612+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.705831+00:00", "framework": "vllm-patch-tokenizer", "intentId": "ea6484f1967547b590d8b6b4526fb6e9", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427609+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.705790+00:00", "framework": "vllm-patch-tokenizer", "intentId": "48dbb20281dc46ae95444bfdae62dc1a", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427607+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.705747+00:00", "framework": "vllm-patch-tokenizer", "intentId": "f377c35a89ad46c294a3cb94ac6cc97c", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427604+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.705705+00:00", "framework": "vllm-patch-tokenizer", "intentId": "28620b36218c41fba0efd9ce967a4232", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427601+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.705659+00:00", "framework": "vllm-patch-tokenizer", "intentId": "daa4ea1ab2234325b8845c87bf0a7b6a", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427598+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.705617+00:00", "framework": "vllm-patch-tokenizer", "intentId": "0f8ea45e9a8e488a845b0d9f22760599", "repoId": "neuralmagic/starcoder2-3b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427596+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.705575+00:00", "framework": "vllm-patch-tokenizer", "intentId": "e53186eea7d04a74b72c35ff403edc80", "repoId": "neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427593+00:00", "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.705532+00:00", "framework": "vllm-patch-tokenizer", "intentId": "ebd250e910e748cea11aa5ad3581866a", "repoId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427590+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.705472+00:00", "framework": "transformers", "intentId": "0b17c833d622437a89dd3304d2fa1cf4", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427588+00:00", "configFingerprint": "0335c7e4668aaa963303ebe91f80d6eb1e7e8d0299011bd85f7e05a4df031dc7", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.705411+00:00", "framework": "transformers", "intentId": "e802730d780c45ae9a4b1b2fe6cee458", "repoId": "aisingapore/SEA-LION-v1-7B-IT-Research", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427585+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.705350+00:00", "framework": "transformers", "intentId": "1a839abc9ec64e7e9dcdcd9ab673aced", "repoId": "LiquidAI/LFM2.5-2.6B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427583+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.705289+00:00", "framework": "transformers", "intentId": "f6e4427ea5e243038178394eeea43d38", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427580+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.705228+00:00", "framework": "transformers", "intentId": "bf0a306a187449938b58fedf78e7dc97", "repoId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427577+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.705167+00:00", "framework": "transformers", "intentId": "a2b2ab4197c446cd83b4f1f29f27470f", "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427575+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.705107+00:00", "framework": "transformers", "intentId": "427f284576464044b7255f7ec8a1f9e2", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427572+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.705046+00:00", "framework": "transformers", "intentId": "27932c6457004a7fbd2d23d6efaff3ab", "repoId": "RedHatAI/starcoder2-3b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427569+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.704985+00:00", "framework": "transformers", "intentId": "9cd7c9b0f7af4bd987c8e06d74f3a069", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427566+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.704924+00:00", "framework": "transformers", "intentId": "e4d015652fb14fcdabc16158f0e703fe", "repoId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427563+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.704862+00:00", "framework": "transformers", "intentId": "db396f6a1f9540d4ae740110285b68a0", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427560+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.704800+00:00", "framework": "transformers", "intentId": "9e7a1402ca7d474598931eabda8e1bc4", "repoId": "BAAI/AquilaMed-RL", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427544+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.704758+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b44996202a114ce68f4f1ed5d78bdf12", "repoId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427539+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.704715+00:00", "framework": "vllm_fix_tokenizer", "intentId": "952f1bd4f23f4a6385b6ebd7d45aa028", "repoId": "pfnet/plamo-3-nict-8b-base", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427536+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.704653+00:00", "framework": "vllm_fix_tokenizer", "intentId": "41284449ddc54efb8224f822eb02a4eb", "repoId": "whcl412/mlx-LycheeAI-coder-1.7b", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427532+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.704611+00:00", "framework": "vllm_fix_tokenizer", "intentId": "7f34b3d00d474e98a40018aaadef4083", "repoId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427521+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.704484+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1c2b03b551bc46d6825428bab76bd4fd", "repoId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427517+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.704441+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5f4dd1d1d5b24cc8a8bacbb1adbdd7af", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427513+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.704398+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c2cc823e1ffd4e2cae3acacb5b93c37f", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427509+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.704356+00:00", "framework": "vllm_fix_tokenizer", "intentId": "33a2f0590fe04efeb39366c1b05f9160", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427502+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.704271+00:00", "framework": "vllm_fix_tokenizer", "intentId": "322b2fd8752c430e885c22df4805f75d", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427498+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.704229+00:00", "framework": "vllm_fix_tokenizer", "intentId": "711f51133fb04171b63c865b62746298", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427494+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.704186+00:00", "framework": "vllm_fix_tokenizer", "intentId": "deeab45d49274acc9dab1178f55ec6b9", "repoId": "neuralmagic/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427491+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.704144+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e0ded25d91334e5a81b2e195cc23cc49", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427487+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.704101+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a36188d65f0c442a81c8a0b2a326c183", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427479+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.704013+00:00", "framework": "vllm_fix_tokenizer", "intentId": "73362ebb20b04c6d937051fe1800d1ce", "repoId": "nm-testing/Meta-Llama-3.1-8B-Instruct-FP8-hf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427462+00:00", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.703864+00:00", "framework": "vllm_tokenizer_patch", "intentId": "017881086afe4798903837c6c77468b9", "repoId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "c3d20cada40b40b5b8f6ae2e5af009fd", "completedAt": "2026-09-21T16:49:29.512236+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.499444+00:00", "framework": "vllm", "intentId": "dbf6555cb7f7401f8f153cc8ee23c45f", "repoId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "c3d20cada40b40b5b8f6ae2e5af009fd", "completedAt": "2026-09-21T16:49:29.512233+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.499386+00:00", "framework": "vllm", "intentId": "9d05978022d44ed698385ac07fc114b9", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"}
{"batchId": "c3d20cada40b40b5b8f6ae2e5af009fd", "completedAt": "2026-09-21T16:49:29.512230+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.499334+00:00", "framework": "vllm-customized", "intentId": "4c8bd7a1a75549238b40ff2a1d67058e", "repoId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
{"batchId": "c3d20cada40b40b5b8f6ae2e5af009fd", "completedAt": "2026-09-21T16:49:29.512227+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.499282+00:00", "framework": "vllm-customized", "intentId": "8a0c4329af36406da6ab88de5f1c25f8", "repoId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
{"batchId": "c3d20cada40b40b5b8f6ae2e5af009fd", "completedAt": "2026-09-21T16:49:29.512224+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.499229+00:00", "framework": "vllm-customized", "intentId": "de5427a0832147f8a74c69628889ee33", "repoId": "TokenRhythm/NeoHorse-1-9B", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
{"batchId": "c3d20cada40b40b5b8f6ae2e5af009fd", "completedAt": "2026-09-21T16:49:29.512222+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.499175+00:00", "framework": "vllm-customized", "intentId": "cb67a1f5054644b78fadde766f89a5ce", "repoId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
{"batchId": "c3d20cada40b40b5b8f6ae2e5af009fd", "completedAt": "2026-09-21T16:49:29.512219+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.499121+00:00", "framework": "vllm-customized", "intentId": "b9684a06db5145a3b0191b55f886f3f4", "repoId": "XHToken/Spark-X2.5-1.7B", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
{"batchId": "c3d20cada40b40b5b8f6ae2e5af009fd", "completedAt": "2026-09-21T16:49:29.512216+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.499062+00:00", "framework": "vllm-customized", "intentId": "a1aa1b9e709b4cbbb0f6a870d538425d", "repoId": "TokenRhythm/NeoHorse-1-4B", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
{"batchId": "c3d20cada40b40b5b8f6ae2e5af009fd", "completedAt": "2026-09-21T16:49:29.512213+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.499005+00:00", "framework": "vllm-customized", "intentId": "3de7bc3b32db426aada1229a46846123", "repoId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "c3d20cada40b40b5b8f6ae2e5af009fd", "completedAt": "2026-09-21T16:49:29.512210+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.498947+00:00", "framework": "vllm-customized", "intentId": "effef78088474a31a63a1280c01c93a8", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "c3d20cada40b40b5b8f6ae2e5af009fd", "completedAt": "2026-09-21T16:49:29.512207+00:00", "configFingerprint": "7d3121b7c0c577ab2334a07716695ad3f4016fc14badec71a6e0fbffc883b16d", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.498890+00:00", "framework": "vllm-customized", "intentId": "b5a8be2e3bae478facf78e622ddcef6b", "repoId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}

16
.modelhub_state/routing_intelligence.json
View File

@@ -1,6 +1,6 @@
{ {
"acceptedByCategory": { "acceptedByCategory": {
"unified_success_first": 2341 "unified_success_first": 2353
}, },
"acceptedByRoute": { "acceptedByRoute": {
"text-generation|Ascend_910-b3|llamacpp": 17, "text-generation|Ascend_910-b3|llamacpp": 17,
@@ -8,7 +8,7 @@
"text-generation|Ascend_910-b3|vllm_tokenizer_patch": 165, "text-generation|Ascend_910-b3|vllm_tokenizer_patch": 165,
"text-generation|Ascend_910-b4|llamacpp": 13, "text-generation|Ascend_910-b4|llamacpp": 13,
"text-generation|Ascend_910-b4|vllm": 28, "text-generation|Ascend_910-b4|vllm": 28,
"text-generation|Ascend_910-b4|vllm_tokenizer_patch": 151, "text-generation|Ascend_910-b4|vllm_tokenizer_patch": 154,
"text-generation|Biren_166m|vllm": 81, "text-generation|Biren_166m|vllm": 81,
"text-generation|Biren_166m|vllm_fix_tokenizer": 130, "text-generation|Biren_166m|vllm_fix_tokenizer": 130,
"text-generation|Cambricon_mlu-370-x4|vllm": 72, "text-generation|Cambricon_mlu-370-x4|vllm": 72,
@@ -25,9 +25,9 @@
"text-generation|Iluvatar_bi-150|vllm_fix_tokenizer": 57, "text-generation|Iluvatar_bi-150|vllm_fix_tokenizer": 57,
"text-generation|Iluvatar_bi-150|vllm_tokenizer_patch": 14, "text-generation|Iluvatar_bi-150|vllm_tokenizer_patch": 14,
"text-generation|Iluvatar_mrv-100|vllm": 63, "text-generation|Iluvatar_mrv-100|vllm": 63,
"text-generation|Kunlunxin_p-800|vllm": 62, "text-generation|Kunlunxin_p-800|vllm": 64,
"text-generation|Kunlunxin_p-800|vllm_fix_tokenizer": 187, "text-generation|Kunlunxin_p-800|vllm_fix_tokenizer": 189,
"text-generation|Kunlunxin_p-800|vllm_tokenizer_patch": 91, "text-generation|Kunlunxin_p-800|vllm_tokenizer_patch": 96,
"text-generation|MetaX_c-500|vllm": 105, "text-generation|MetaX_c-500|vllm": 105,
"text-generation|Mthreads_s4000|llamacpp": 17, "text-generation|Mthreads_s4000|llamacpp": 17,
"text-generation|Mthreads_s4000|vllm": 106, "text-generation|Mthreads_s4000|vllm": 106,
@@ -38,8 +38,8 @@
"text-generation|hygon_k100-ai|vllm": 26, "text-generation|hygon_k100-ai|vllm": 26,
"text-generation|hygon_k100-ai|vllm-patch-tokenizer": 134 "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 134
}, },
"acceptedSinceRefresh": 2341, "acceptedSinceRefresh": 2353,
"acceptedTotal": 2341, "acceptedTotal": 2353,
"generatedAt": "2026-09-21T18:17:49.831178+00:00", "generatedAt": "2026-09-21T18:32:47.159796+00:00",
"version": 1 "version": 1
} }

14
ledger/submissions.jsonl
View File

@@ -1014,8 +1014,6 @@
{"framework": "transformers", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-quantized.w8a16", "modelId": "RedHatAI/starcoder2-7b-quantized.w8a16", "submitTime": "2026-09-21T18:13:42.077548+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5005304", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-150"} {"framework": "transformers", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-quantized.w8a16", "modelId": "RedHatAI/starcoder2-7b-quantized.w8a16", "submitTime": "2026-09-21T18:13:42.077548+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5005304", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-150"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "submitTime": "2026-09-21T18:14:20.635969+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5005325", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-iluvatar-bi-150"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "submitTime": "2026-09-21T18:14:20.635969+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5005325", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-iluvatar-bi-150"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "submitTime": "2026-09-21T18:14:31.787220+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5005326", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-iluvatar-bi-150"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "submitTime": "2026-09-21T18:14:31.787220+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5005326", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-iluvatar-bi-150"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-it-quantized.w8a16", "modelId": "neuralmagic/gemma-2-2b-it-quantized.w8a16", "submitTime": "2026-09-20T21:37:47.191312+00:00", "targetGpu": "Biren_166m", "taskId": "4988063", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/sbintuitions/sarashina2.2-3b-instruct-v0.1", "modelId": "sbintuitions/sarashina2.2-3b-instruct-v0.1", "submitTime": "2026-09-20T22:29:12.187825+00:00", "targetGpu": "Biren_166m", "taskId": "4988752", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-4B", "modelId": "TokenRhythm/NeoHorse-1-4B", "submitTime": "2026-09-20T22:29:12.193862+00:00", "targetGpu": "Biren_166m", "taskId": "4988754", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-4B", "modelId": "TokenRhythm/NeoHorse-1-4B", "submitTime": "2026-09-20T22:29:12.193862+00:00", "targetGpu": "Biren_166m", "taskId": "4988754", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-8B-A1B", "modelId": "LiquidAI/LFM2.5-8B-A1B", "submitTime": "2026-09-20T22:29:12.195398+00:00", "targetGpu": "Biren_166m", "taskId": "4988751", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-8B-A1B", "modelId": "LiquidAI/LFM2.5-8B-A1B", "submitTime": "2026-09-20T22:29:12.195398+00:00", "targetGpu": "Biren_166m", "taskId": "4988751", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "submitTime": "2026-09-20T23:11:16.555645+00:00", "targetGpu": "Biren_166m", "taskId": "4989302", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "submitTime": "2026-09-20T23:11:16.555645+00:00", "targetGpu": "Biren_166m", "taskId": "4989302", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
@@ -1215,3 +1213,15 @@
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "modelId": "neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "submitTime": "2026-09-21T17:47:54.565894+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5004980", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-iluvatar-bi-150"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "modelId": "neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "submitTime": "2026-09-21T17:47:54.565894+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5004980", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-iluvatar-bi-150"}
{"framework": "transformers", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-3b-FP8", "modelId": "RedHatAI/starcoder2-3b-FP8", "submitTime": "2026-09-21T17:52:34.537339+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5005043", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-150"} {"framework": "transformers", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-3b-FP8", "modelId": "RedHatAI/starcoder2-3b-FP8", "submitTime": "2026-09-21T17:52:34.537339+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5005043", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-150"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-MLX", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "submitTime": "2026-09-21T17:56:19.767756+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5005093", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-bi-150"} {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-MLX", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "submitTime": "2026-09-21T17:56:19.767756+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5005093", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-bi-150"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-Non-Uniform-compressed-tensors", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-Non-Uniform-compressed-tensors", "submitTime": "2026-09-21T18:22:48.748348+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5005405", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8-channel-a8-tensor", "modelId": "nm-testing/tinyllama-oneshot-w8-channel-a8-tensor", "submitTime": "2026-09-21T18:22:48.751608+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5005404", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-llama3-8b-Instruct-SmoothQuant-Fp8", "modelId": "nm-testing/Meta-llama3-8b-Instruct-SmoothQuant-Fp8", "submitTime": "2026-09-21T18:22:48.749631+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5005403", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t", "modelId": "nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t", "submitTime": "2026-09-21T18:22:48.756508+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5005406", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w4a16-channel-v2", "modelId": "nm-testing/tinyllama-oneshot-w4a16-channel-v2", "submitTime": "2026-09-21T18:22:48.845075+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5005433", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/nm-testing/nonuniform", "modelId": "nm-testing/nonuniform", "submitTime": "2026-09-21T18:24:25.745057+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5005434", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-kunlunxin-p-800"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "submitTime": "2026-09-21T18:24:25.894740+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5005435", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-kunlunxin-p-800"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-FP8", "modelId": "RedHatAI/starcoder2-7b-FP8", "submitTime": "2026-09-21T18:24:26.079648+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5005436", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-kunlunxin-p-800"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w4a16", "modelId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w4a16", "submitTime": "2026-09-21T18:24:26.292133+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5005437", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-kunlunxin-p-800"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-base-32K", "modelId": "CohereLabs/tiny-aya-base-32K", "submitTime": "2026-09-21T18:24:26.404225+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5005438", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-kunlunxin-p-800"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "modelId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "submitTime": "2026-09-21T18:24:26.526740+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5005439", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-kunlunxin-p-800"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B-IT-GPTQ", "modelId": "aisingapore/SEA-LION-v1-7B-IT-GPTQ", "submitTime": "2026-09-21T18:24:26.638177+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5005440", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-kunlunxin-p-800"}

14
manifest.json
View File

@@ -10,16 +10,16 @@
".modelhub_state/queue_cleanup_latest.json": "96de561331568d32afa16a3d1299e6bf6ad1009a8239697991dc48f28baf298b", ".modelhub_state/queue_cleanup_latest.json": "96de561331568d32afa16a3d1299e6bf6ad1009a8239697991dc48f28baf298b",
".modelhub_state/recent_outcomes.jsonl": "761386dbe1a1cb3e15422a3ad1434c5c04e712a852e10c411c2eb3fa31e1698b", ".modelhub_state/recent_outcomes.jsonl": "761386dbe1a1cb3e15422a3ad1434c5c04e712a852e10c411c2eb3fa31e1698b",
".modelhub_state/recovery_active_tasks.jsonl": "6ca21906bd22528ce7f4b9602d3c9f3e1350ac4955880121d3cfbd8d43308878", ".modelhub_state/recovery_active_tasks.jsonl": "6ca21906bd22528ce7f4b9602d3c9f3e1350ac4955880121d3cfbd8d43308878",
".modelhub_state/recovery_intents.jsonl": "ba983686a13e26e5c4ee0351a680b0e84c1f0ec7fb38964ea47ff63e9f0f493b", ".modelhub_state/recovery_intents.jsonl": "ba340446000b497c19b754d639676bad3c91f63fb8034d925a9257c462d37680",
".modelhub_state/routing_intelligence.json": "ed2e6d51b340642eaf3181120fefb6520c100b5bc2223f380036da6bae6fc2e4", ".modelhub_state/routing_intelligence.json": "fbb1c51b135699d2f8b0507946ea95e91c917f90753c964672d9559d26c0590c",
".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989", ".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989",
".modelhub_state/worker_crashes.jsonl": "07505b69e0b050da5f90f8b046a3069d3e1ca2574ca39896bc7d8a66293167f7", ".modelhub_state/worker_crashes.jsonl": "07505b69e0b050da5f90f8b046a3069d3e1ca2574ca39896bc7d8a66293167f7",
"ledger/submissions.jsonl": "180959aec410053184a1001b337b8cd2ee3ebd63aafa2d4411ab200b2f3ba15b", "ledger/submissions.jsonl": "063dd08fa16554aa9740d440a0b08a583e37f1eacaad775076ef39d4eac752bf",
"outcomes/submissions.jsonl": "01738a680ce6f553218c5faade18a36382c24badca7d661f8c8912d55555e350" "outcomes/submissions.jsonl": "b6c076e4d078d1a049982eb6cbfbeb7b02c806b83c1167c9b802dd65cd72a43b"
}, },
"generation": 11601, "generation": 11602,
"phase": "intent", "phase": "result",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-09-21T18:22:37.346309+00:00", "updatedAt": "2026-09-21T18:32:47.428045+00:00",
"writerId": "8b35139af6674067a339a670222d4b67" "writerId": "8b35139af6674067a339a670222d4b67"
} }

12
outcomes/submissions.jsonl
View File

@@ -1168,3 +1168,15 @@
{"failReason": null, "framework": "transformers", "lastSyncTime": null, "modelId": "RedHatAI/starcoder2-7b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7857298896, "estimatedRequiredGiB": 8.785, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 7860673720, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 7400416256, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7860673720}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T18:13:42.077548+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5005304", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "transformers", "lastSyncTime": null, "modelId": "RedHatAI/starcoder2-7b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7857298896, "estimatedRequiredGiB": 8.785, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 7860673720, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 7400416256, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7860673720}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T18:13:42.077548+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5005304", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23420419700, "estimatedRequiredGiB": 26.214, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 23455515266, "modelscopeLicense": "mit", "modelscopeParams": 19528501104, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 23455515266}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T18:14:20.635969+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5005325", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23420419700, "estimatedRequiredGiB": 26.214, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 23455515266, "modelscopeLicense": "mit", "modelscopeParams": 19528501104, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 23455515266}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T18:14:20.635969+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5005325", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 658540250, "estimatedRequiredGiB": 0.741, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 663410366, "modelscopeLicense": "other", "modelscopeParams": 182975232, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": {"model_load": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-09-21T04:36:00.569307+00:00", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0}, "repositoryOnDiskBytes": 663410366}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T18:14:31.787220+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5005326", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 658540250, "estimatedRequiredGiB": 0.741, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 663410366, "modelscopeLicense": "other", "modelscopeParams": 182975232, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": {"model_load": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-09-21T04:36:00.569307+00:00", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0}, "repositoryOnDiskBytes": 663410366}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T18:14:31.787220+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5005326", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-Non-Uniform-compressed-tensors", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20041566112, "estimatedRequiredGiB": 22.408, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 20050750527, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-09-21T15:02:24.876390+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 20050750527}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T18:22:48.748348+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5005405", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "nm-testing/tinyllama-oneshot-w8-channel-a8-tensor", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1232059012, "estimatedRequiredGiB": 1.379, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1233907698, "modelscopeLicense": null, "modelscopeParams": 1100048384, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-09-21T15:02:24.876390+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 1233907698}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T18:22:48.751608+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5005404", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "nm-testing/Meta-llama3-8b-Instruct-SmoothQuant-Fp8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9081287016, "estimatedRequiredGiB": 10.159, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9090490505, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-09-21T15:02:24.876390+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 9090490505}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T18:22:48.749631+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5005403", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3054596816, "estimatedRequiredGiB": 3.416, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 3056444703, "modelscopeLicense": null, "modelscopeParams": 1122504704, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3056444703}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T18:22:48.756508+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5005406", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "nm-testing/tinyllama-oneshot-w4a16-channel-v2", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 747618112, "estimatedRequiredGiB": 0.838, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 749466433, "modelscopeLicense": null, "modelscopeParams": 1100048384, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 749466433}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T18:22:48.845075+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5005433", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "nm-testing/nonuniform", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9517467172, "estimatedRequiredGiB": 10.647, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9526650722, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9526650722}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T18:24:25.745057+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5005434", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14293356304, "estimatedRequiredGiB": 15.977, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 14295851911, "modelscopeLicense": "mit", "modelscopeParams": 13960238080, "modelscopeTags": ["license:mit", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14295851911}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T18:24:25.894740+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5005435", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/starcoder2-7b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7855165704, "estimatedRequiredGiB": 8.783, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 7858540940, "modelscopeLicense": "other", "modelscopeParams": 7400416256, "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": 7858540940}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T18:24:26.079648+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5005436", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w4a16", "modelProfile": {"architectures": ["MistralForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8308282608, "estimatedRequiredGiB": 9.319, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral", "modelscopeFileSize": 8338221450, "modelscopeLicense": "llama2", "modelscopeParams": 12247782400, "modelscopeTags": ["license:llama2", "model_type:mistral", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8338221450}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T18:24:26.292133+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5005437", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "CohereLabs/tiny-aya-base-32K", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730839322, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:long-context", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730839322}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T18:24:26.404225+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5005438", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084040952, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093251763, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "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": 9093251763}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T18:24:26.526740+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5005439", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "aisingapore/SEA-LION-v1-7B-IT-GPTQ", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5469228368, "estimatedRequiredGiB": 6.118, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mpt", "modelscopeFileSize": 5473985594, "modelscopeLicense": "mit", "modelscopeParams": 1922048000, "modelscopeTags": ["license:mit", "model_type:mpt", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5473985594}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T18:24:26.638177+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5005440", "taskType": "text-generation", "verifyResult": null}