From 45d47ec1cb79ae295594138709ca43ecfe71b77c Mon Sep 17 00:00:00 2001 From: CoolBoy <2269097679@qq.com> Date: Sun, 20 Sep 2026 03:40:44 +0000 Subject: [PATCH] state: generation 10139 (result) --- .modelhub_state/recovery_intents.jsonl | 30 +++++++++++------------ .modelhub_state/routing_intelligence.json | 18 +++++++------- ledger/submissions.jsonl | 30 +++++++++++------------ manifest.json | 14 +++++------ outcomes/submissions.jsonl | 15 ++++++++++++ 5 files changed, 61 insertions(+), 46 deletions(-) diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 483427eefb..1f4b148a73 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -1276,21 +1276,21 @@ {"batchId": "5177472595af4810828b15c6f8cedaf5", "completedAt": "2026-09-20T03:30:31.289121+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:30:22.939559+00:00", "framework": "vllm", "intentId": "c7611e6b92f84997ad01a0afb937cfae", "lastModified": "2026-09-09T06:27:24+00:00", "modelAddress": "https://modelscope.cn/models/ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "reason": null, "reconciledAt": "2026-09-20T03:36:12.230019+00:00", "repoId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "4969818", "taskType": "text-generation"} {"batchId": "5177472595af4810828b15c6f8cedaf5", "completedAt": "2026-09-20T03:30:31.289123+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:30:22.939616+00:00", "framework": "vllm", "intentId": "aa4acbf9f5f343fe829252e21693607e", "lastModified": "2026-08-28T05:30:04+00:00", "modelAddress": "https://modelscope.cn/models/whcl412/mlx-LycheeAI-coder-1.7b", "reason": null, "reconciledAt": "2026-09-20T03:36:12.231282+00:00", "repoId": "whcl412/mlx-LycheeAI-coder-1.7b", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "4969817", "taskType": "text-generation"} {"batchId": "cc8e7b78004249398e38942d3706b440", "completedAt": "2026-09-20T03:35:20.314835+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:35:12.528880+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0f782aa492824b6fb074e98f013f64f9", "lastModified": "2026-08-26T20:08:57+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "reason": null, "reconciledAt": "2026-09-20T03:36:12.231737+00:00", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "4969892", "taskType": "text-generation"} -{"batchId": "63dd409721f8427398583e231542cb8f", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:40:34.950838+00:00", "framework": "vllm-mlu", "intentId": "29f0bc1cf117473d9a86223d2c45baf2", "lastModified": "2026-08-24T20:31:44+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3-8B-Instruct-quantized.w8a8", "repoId": "neuralmagic/Meta-Llama-3-8B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} -{"batchId": "63dd409721f8427398583e231542cb8f", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:40:34.950958+00:00", "framework": "vllm-mlu", "intentId": "ade342e8a7994a9cb148c0a47dba415b", "lastModified": "2026-08-24T20:26:05+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Qwen2-7B-Instruct-quantized.w8a8", "repoId": "neuralmagic/Qwen2-7B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} -{"batchId": "63dd409721f8427398583e231542cb8f", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:40:34.951011+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a9fb917b2cc04df584879b99b1f5361b", "lastModified": "2026-08-25T12:06:29+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-8B-A1B", "repoId": "LiquidAI/LFM2.5-8B-A1B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "63dd409721f8427398583e231542cb8f", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:40:34.951057+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ddebe1b327fc4c5db3bb7c7585b219d6", "lastModified": "2026-08-24T20:36:29+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "63dd409721f8427398583e231542cb8f", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:40:34.951100+00:00", "framework": "vllm_tokenizer_patch", "intentId": "69f00cc217204d2ab3b3bb0bcc91f5da", "lastModified": "2026-08-24T20:25:10+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-quantized.w8a16", "repoId": "neuralmagic/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} -{"batchId": "63dd409721f8427398583e231542cb8f", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:40:34.951141+00:00", "framework": "vllm_tokenizer_patch", "intentId": "113adf0d69d441a8b27656a079f26d93", "lastModified": "2026-08-24T20:38:01+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/SmolLM-135M-Instruct-quantized.w8a8", "repoId": "neuralmagic/SmolLM-135M-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} -{"batchId": "63dd409721f8427398583e231542cb8f", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:40:34.951179+00:00", "framework": "vllm_tokenizer_patch", "intentId": "9ed2d64bccd84125a9afee010d63a64d", "lastModified": "2026-08-24T20:30:03+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-quantized.w4a16", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} -{"batchId": "63dd409721f8427398583e231542cb8f", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:40:34.951217+00:00", "framework": "vllm_tokenizer_patch", "intentId": "dfad85074942455aafc4f0a5484ba394", "lastModified": "2026-08-24T20:36:33+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} -{"batchId": "63dd409721f8427398583e231542cb8f", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:40:34.951254+00:00", "framework": "vllm_tokenizer_patch", "intentId": "97f66ea1a2204b50bc4ee8d65be871da", "lastModified": "2026-08-24T20:29:58+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-quantized.w8a16", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} -{"batchId": "63dd409721f8427398583e231542cb8f", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:40:34.951292+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f19027aa288142dba816830f0ea08721", "lastModified": "2026-08-24T22:06:31+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-FP8", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} -{"batchId": "63dd409721f8427398583e231542cb8f", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:40:34.951329+00:00", "framework": "vllm-patch-tokenizer", "intentId": "af59589d2cbe444fa9f4e722f819ac73", "lastModified": "2026-08-26T12:23:32+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"} -{"batchId": "63dd409721f8427398583e231542cb8f", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:40:34.951372+00:00", "framework": "vllm", "intentId": "dbdd6683b36b4ef298d7160f423144ea", "lastModified": "2026-08-24T20:36:30+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "repoId": "neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} -{"batchId": "63dd409721f8427398583e231542cb8f", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:40:34.951421+00:00", "framework": "vllm", "intentId": "b40ac99fc2644917aeba138a4ee25e2d", "lastModified": "2026-08-24T20:38:11+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-quantized.w8a16", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} -{"batchId": "63dd409721f8427398583e231542cb8f", "configFingerprint": "f49713b9fe8e3e7683ab2722544c85a44993bcd72b9421c1599f634e68b3a2f7", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:40:34.951468+00:00", "framework": "vllm", "intentId": "edb59f1232c14b8783296fa28311e566", "lastModified": "2026-08-24T20:34:54+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-360M-Instruct-quantized.w8a8", "repoId": "RedHatAI/SmolLM-360M-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} -{"batchId": "63dd409721f8427398583e231542cb8f", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:40:34.951515+00:00", "framework": "vllm", "intentId": "1185bb045aa845d1a8e8031101422f33", "lastModified": "2026-08-25T12:09:43+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-2.6B", "repoId": "LiquidAI/LFM2.5-2.6B", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} +{"batchId": "63dd409721f8427398583e231542cb8f", "completedAt": "2026-09-20T03:40:44.644474+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:40:34.950838+00:00", "framework": "vllm-mlu", "intentId": "29f0bc1cf117473d9a86223d2c45baf2", "lastModified": "2026-08-24T20:31:44+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3-8B-Instruct-quantized.w8a8", "reason": null, "repoId": "neuralmagic/Meta-Llama-3-8B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969964", "taskType": "text-generation"} +{"batchId": "63dd409721f8427398583e231542cb8f", "completedAt": "2026-09-20T03:40:44.644492+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:40:34.950958+00:00", "framework": "vllm-mlu", "intentId": "ade342e8a7994a9cb148c0a47dba415b", "lastModified": "2026-08-24T20:26:05+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Qwen2-7B-Instruct-quantized.w8a8", "reason": null, "repoId": "neuralmagic/Qwen2-7B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969956", "taskType": "text-generation"} +{"batchId": "63dd409721f8427398583e231542cb8f", "completedAt": "2026-09-20T03:40:44.644495+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:40:34.951011+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a9fb917b2cc04df584879b99b1f5361b", "lastModified": "2026-08-25T12:06:29+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-8B-A1B", "reason": null, "repoId": "LiquidAI/LFM2.5-8B-A1B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "4969966", "taskType": "text-generation"} +{"batchId": "63dd409721f8427398583e231542cb8f", "completedAt": "2026-09-20T03:40:44.644498+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:40:34.951057+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ddebe1b327fc4c5db3bb7c7585b219d6", "lastModified": "2026-08-24T20:36:29+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "reason": null, "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "4969955", "taskType": "text-generation"} +{"batchId": "63dd409721f8427398583e231542cb8f", "completedAt": "2026-09-20T03:40:44.644501+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:40:34.951100+00:00", "framework": "vllm_tokenizer_patch", "intentId": "69f00cc217204d2ab3b3bb0bcc91f5da", "lastModified": "2026-08-24T20:25:10+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-quantized.w8a16", "reason": null, "repoId": "neuralmagic/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4969963", "taskType": "text-generation"} +{"batchId": "63dd409721f8427398583e231542cb8f", "completedAt": "2026-09-20T03:40:44.644503+00:00", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:40:34.951141+00:00", "framework": "vllm_tokenizer_patch", "intentId": "113adf0d69d441a8b27656a079f26d93", "lastModified": "2026-08-24T20:38:01+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/SmolLM-135M-Instruct-quantized.w8a8", "reason": null, "repoId": "neuralmagic/SmolLM-135M-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4969958", "taskType": "text-generation"} +{"batchId": "63dd409721f8427398583e231542cb8f", "completedAt": "2026-09-20T03:40:44.644505+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:40:34.951179+00:00", "framework": "vllm_tokenizer_patch", "intentId": "9ed2d64bccd84125a9afee010d63a64d", "lastModified": "2026-08-24T20:30:03+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-quantized.w4a16", "reason": null, "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4969959", "taskType": "text-generation"} +{"batchId": "63dd409721f8427398583e231542cb8f", "completedAt": "2026-09-20T03:40:44.644507+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:40:34.951217+00:00", "framework": "vllm_tokenizer_patch", "intentId": "dfad85074942455aafc4f0a5484ba394", "lastModified": "2026-08-24T20:36:33+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "reason": null, "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4969965", "taskType": "text-generation"} +{"batchId": "63dd409721f8427398583e231542cb8f", "completedAt": "2026-09-20T03:40:44.644509+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:40:34.951254+00:00", "framework": "vllm_tokenizer_patch", "intentId": "97f66ea1a2204b50bc4ee8d65be871da", "lastModified": "2026-08-24T20:29:58+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-quantized.w8a16", "reason": null, "repoId": "RedHatAI/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4969961", "taskType": "text-generation"} +{"batchId": "63dd409721f8427398583e231542cb8f", "completedAt": "2026-09-20T03:40:44.644511+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:40:34.951292+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f19027aa288142dba816830f0ea08721", "lastModified": "2026-08-24T22:06:31+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-FP8", "reason": null, "repoId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4969960", "taskType": "text-generation"} +{"batchId": "63dd409721f8427398583e231542cb8f", "completedAt": "2026-09-20T03:40:44.644514+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:40:34.951329+00:00", "framework": "vllm-patch-tokenizer", "intentId": "af59589d2cbe444fa9f4e722f819ac73", "lastModified": "2026-08-26T12:23:32+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "reason": null, "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "hygon_k100-ai", "taskId": "4969957", "taskType": "text-generation"} +{"batchId": "63dd409721f8427398583e231542cb8f", "completedAt": "2026-09-20T03:40:44.644516+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:40:34.951372+00:00", "framework": "vllm", "intentId": "dbdd6683b36b4ef298d7160f423144ea", "lastModified": "2026-08-24T20:36:30+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "reason": null, "repoId": "neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969962", "taskType": "text-generation"} +{"batchId": "63dd409721f8427398583e231542cb8f", "completedAt": "2026-09-20T03:40:44.644518+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:40:34.951421+00:00", "framework": "vllm", "intentId": "b40ac99fc2644917aeba138a4ee25e2d", "lastModified": "2026-08-24T20:38:11+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-quantized.w8a16", "reason": null, "repoId": "RedHatAI/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969969", "taskType": "text-generation"} +{"batchId": "63dd409721f8427398583e231542cb8f", "completedAt": "2026-09-20T03:40:44.644520+00:00", "configFingerprint": "f49713b9fe8e3e7683ab2722544c85a44993bcd72b9421c1599f634e68b3a2f7", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:40:34.951468+00:00", "framework": "vllm", "intentId": "edb59f1232c14b8783296fa28311e566", "lastModified": "2026-08-24T20:34:54+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-360M-Instruct-quantized.w8a8", "reason": null, "repoId": "RedHatAI/SmolLM-360M-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969967", "taskType": "text-generation"} +{"batchId": "63dd409721f8427398583e231542cb8f", "completedAt": "2026-09-20T03:40:44.644521+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:40:34.951515+00:00", "framework": "vllm", "intentId": "1185bb045aa845d1a8e8031101422f33", "lastModified": "2026-08-25T12:09:43+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-2.6B", "reason": null, "repoId": "LiquidAI/LFM2.5-2.6B", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969968", "taskType": "text-generation"} {"batchId": "a0638aa6b9d441fc8127d1ff98b0380e", "completedAt": "2026-09-20T02:22:36.529135+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-10T13:27:22.633245+00:00", "framework": "vllm", "intentId": "8986a9476a034876a874432fe981a93c", "repoId": "laion/swesmith-nl2bash-stack-bugsseq", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "success", "targetGpu": "Biren_166m", "taskId": "4760700", "taskType": "text-generation"} {"batchId": "3601d2529e2f4dbab4abc91721a031a6", "completedAt": "2026-09-20T01:08:42.115049+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-19T12:27:15.291074+00:00", "framework": "vllm_tokenizer_patch", "intentId": "56909ec2a21e4e3f9e0a55deb70d46c0", "repoId": "Arain119/Sophia", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "failed", "targetGpu": "Ascend_910-b3", "taskId": "4956471", "taskType": "text-generation"} {"batchId": "17f9bc75c9254b23a97517096a945dfd", "completedAt": "2026-09-20T00:27:18.357432+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-09T17:53:27.791335+00:00", "framework": "vllm-mlu", "intentId": "e8b41bd8a15a4f4ab9051c3e998dfc85", "repoId": "laion/swesmith-nl2bash-stack-bugsseq", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "success", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4744096", "taskType": "text-generation"} diff --git a/.modelhub_state/routing_intelligence.json b/.modelhub_state/routing_intelligence.json index 84cf31991e..23c6cf57a0 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,19 +1,19 @@ { "acceptedByCategory": { - "unified_success_first": 1416 + "unified_success_first": 1431 }, "acceptedByRoute": { "text-generation|Ascend_910-b3|llamacpp": 17, "text-generation|Ascend_910-b3|vllm": 30, - "text-generation|Ascend_910-b3|vllm_tokenizer_patch": 100, + "text-generation|Ascend_910-b3|vllm_tokenizer_patch": 106, "text-generation|Ascend_910-b4|llamacpp": 13, "text-generation|Ascend_910-b4|vllm": 13, "text-generation|Ascend_910-b4|vllm_tokenizer_patch": 93, "text-generation|Biren_166m|vllm": 63, "text-generation|Biren_166m|vllm_fix_tokenizer": 13, - "text-generation|Cambricon_mlu-370-x4|vllm": 34, + "text-generation|Cambricon_mlu-370-x4|vllm": 38, "text-generation|Cambricon_mlu-370-x4|vllm-customized": 1, - "text-generation|Cambricon_mlu-370-x4|vllm-mlu": 73, + "text-generation|Cambricon_mlu-370-x4|vllm-mlu": 75, "text-generation|Cambricon_mlu-370-x8|vllm": 18, "text-generation|Cambricon_mlu-370-x8|vllm-customized": 11, "text-generation|Cambricon_mlu-370-x8|vllm-mlu": 79, @@ -23,7 +23,7 @@ "text-generation|Iluvatar_bi-150|vllm_fix_tokenizer": 5, "text-generation|Iluvatar_mrv-100|vllm": 57, "text-generation|Kunlunxin_p-800|vllm": 1, - "text-generation|Kunlunxin_p-800|vllm_fix_tokenizer": 147, + "text-generation|Kunlunxin_p-800|vllm_fix_tokenizer": 149, "text-generation|Kunlunxin_p-800|vllm_tokenizer_patch": 30, "text-generation|MetaX_c-500|vllm": 101, "text-generation|Mthreads_s4000|llamacpp": 17, @@ -33,10 +33,10 @@ "text-generation|Vastai_va16|vllm_fix_tokenizer": 52, "text-generation|hygon_k100-ai|llamacpp": 18, "text-generation|hygon_k100-ai|vllm": 22, - "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 90 + "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 91 }, - "acceptedSinceRefresh": 1416, - "acceptedTotal": 1416, - "generatedAt": "2026-09-20T03:35:20.268114+00:00", + "acceptedSinceRefresh": 1431, + "acceptedTotal": 1431, + "generatedAt": "2026-09-20T03:40:44.569090+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index daf721a832..38a0cbe47c 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -767,21 +767,6 @@ {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "submitTime": "2026-09-20T03:30:31.141968+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969818", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-ascend-910-b4"} {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whcl412/mlx-LycheeAI-coder-1.7b", "modelId": "whcl412/mlx-LycheeAI-coder-1.7b", "submitTime": "2026-09-20T03:30:31.153489+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969817", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-ascend-910-b4"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "submitTime": "2026-09-20T03:35:13.265606+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969892", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"} -{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-35B-A3B-MLX-6bit", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-MLX-6bit", "submitTime": "2026-09-09T21:08:32.684861+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746455", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"} -{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/mlx-community/Devstral-Small-2-24B-Instruct-2512-OptiQ-4bit", "modelId": "mlx-community/Devstral-Small-2-24B-Instruct-2512-OptiQ-4bit", "submitTime": "2026-09-14T19:47:58.577906+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4856415", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} -{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-e4b-it-OptiQ-4bit", "modelId": "mlx-community/gemma-4-e4b-it-OptiQ-4bit", "submitTime": "2026-09-14T20:04:19.387527+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4856586", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} -{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-e2b-it-OptiQ-4bit", "modelId": "mlx-community/gemma-4-e2b-it-OptiQ-4bit", "submitTime": "2026-09-14T20:04:19.385502+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4856587", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} -{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit", "modelId": "mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit", "submitTime": "2026-09-14T20:21:39.119992+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4856789", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} -{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "modelId": "mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "submitTime": "2026-09-14T20:36:23.395422+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4856934", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} -{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/cyankiwi/Ornith-1.5-35B-A3B-AWQ-INT4", "modelId": "cyankiwi/Ornith-1.5-35B-A3B-AWQ-INT4", "submitTime": "2026-09-08T23:02:51.933574+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729525", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"} -{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/empero-ai/Qwen3.8-9B-Distill", "modelId": "empero-ai/Qwen3.8-9B-Distill", "submitTime": "2026-09-08T23:02:51.939534+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729523", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"} -{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RWKV/RWKV7-7.2B-20260805", "modelId": "RWKV/RWKV7-7.2B-20260805", "submitTime": "2026-09-08T23:02:52.096464+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729531", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"} -{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/groxaxo/Qwen3.8-27B-GPTQ-Pro-4bit-g64-calib128", "modelId": "groxaxo/Qwen3.8-27B-GPTQ-Pro-4bit-g64-calib128", "submitTime": "2026-09-09T21:08:22.091584+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746446", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"} -{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/FlagRelease/DeepSeek-R1-Distill-Qwen-1.5B-mthreads-FlagOS", "modelId": "FlagRelease/DeepSeek-R1-Distill-Qwen-1.5B-mthreads-FlagOS", "submitTime": "2026-09-09T21:08:32.656390+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746454", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"} -{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-NVFP4", "modelId": "primitive-ai/Nex-N2.5-mini-NVFP4", "submitTime": "2026-09-10T14:46:30.894640+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4761529", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"} -{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "submitTime": "2026-09-10T14:46:30.888510+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4761528", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"} -{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-FP8", "modelId": "primitive-ai/Nex-N2.5-mini-FP8", "submitTime": "2026-09-10T14:46:30.890611+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4761532", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"} -{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/mlx-community/Ornith-1.5-35B-A3B-8bit", "modelId": "mlx-community/Ornith-1.5-35B-A3B-8bit", "submitTime": "2026-09-12T16:07:22.080195+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4804755", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"} {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "submitTime": "2026-09-08T16:07:42.654192+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4722475", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RWKV/RWKV7-2.9B-20260805", "modelId": "RWKV/RWKV7-2.9B-20260805", "submitTime": "2026-09-09T21:08:22.094532+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746447", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"} {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "submitTime": "2026-09-09T00:13:45.146237+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4730594", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"} @@ -962,3 +947,18 @@ {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "submitTime": "2026-09-20T03:25:32.546681+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4969665", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-iluvatar-bi-150"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "submitTime": "2026-09-20T03:25:32.539673+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4969663", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-iluvatar-bi-150"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/EschaLabs/Qwen3.8-27B-Escha-W2", "modelId": "EschaLabs/Qwen3.8-27B-Escha-W2", "submitTime": "2026-09-20T03:25:32.535865+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4969660", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-iluvatar-bi-150"} +{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3-8B-Instruct-quantized.w8a8", "modelId": "neuralmagic/Meta-Llama-3-8B-Instruct-quantized.w8a8", "submitTime": "2026-09-20T03:40:37.351352+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969964", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"} +{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/neuralmagic/Qwen2-7B-Instruct-quantized.w8a8", "modelId": "neuralmagic/Qwen2-7B-Instruct-quantized.w8a8", "submitTime": "2026-09-20T03:40:37.293456+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969956", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"} +{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-8B-A1B", "modelId": "LiquidAI/LFM2.5-8B-A1B", "submitTime": "2026-09-20T03:40:37.353529+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969966", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"} +{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "modelId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "submitTime": "2026-09-20T03:40:37.335603+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969955", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"} +{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-quantized.w8a16", "modelId": "neuralmagic/gemma-2-2b-quantized.w8a16", "submitTime": "2026-09-20T03:40:37.347716+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969963", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} +{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/neuralmagic/SmolLM-135M-Instruct-quantized.w8a8", "modelId": "neuralmagic/SmolLM-135M-Instruct-quantized.w8a8", "submitTime": "2026-09-20T03:40:37.349301+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969958", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} +{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-quantized.w4a16", "modelId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w4a16", "submitTime": "2026-09-20T03:40:37.355419+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969959", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} +{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "submitTime": "2026-09-20T03:40:37.357907+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969965", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} +{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-quantized.w8a16", "modelId": "RedHatAI/starcoder2-7b-quantized.w8a16", "submitTime": "2026-09-20T03:40:37.343922+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969961", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} +{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-FP8", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "submitTime": "2026-09-20T03:40:37.340106+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969960", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} +{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "submitTime": "2026-09-20T03:40:37.346146+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969957", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"} +{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "modelId": "neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "submitTime": "2026-09-20T03:40:37.342058+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969962", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x4"} +{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-quantized.w8a16", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a16", "submitTime": "2026-09-20T03:40:44.501444+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969969", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x4"} +{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-360M-Instruct-quantized.w8a8", "modelId": "RedHatAI/SmolLM-360M-Instruct-quantized.w8a8", "submitTime": "2026-09-20T03:40:44.505215+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969967", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x4"} +{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-2.6B", "modelId": "LiquidAI/LFM2.5-2.6B", "submitTime": "2026-09-20T03:40:44.507984+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969968", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x4"} diff --git a/manifest.json b/manifest.json index 55830a089a..4819fdb907 100644 --- a/manifest.json +++ b/manifest.json @@ -9,16 +9,16 @@ ".modelhub_state/queue_cleanup_latest.json": "21a630cefff5c090992ca8360dafe8435b598ca2102f1b9990df6496329a9afe", ".modelhub_state/recent_outcomes.jsonl": "8b230beac27183f4f5f556eaa061dbc77bdcc47b761f379a572673e0fba55aaa", ".modelhub_state/recovery_active_tasks.jsonl": "eb2720d888cbbe5efb715aec8ee88f5638aea69cde0d05588e9933de0252b8ea", - ".modelhub_state/recovery_intents.jsonl": "6484f9283eaaf5aa3aec2bdaf9ce9e5bd164721962b354d340b4ad343a969690", - ".modelhub_state/routing_intelligence.json": "f8111a32fa73b9bb75118e01eb4c78e9754b5302f97440fc5363ca55036788a6", + ".modelhub_state/recovery_intents.jsonl": "9ae09143ea629056c59bbc7bae592f46b3501b7e81f71f2a2ec3cc07223a98bd", + ".modelhub_state/routing_intelligence.json": "cc43ea2cbdc7a6ad1d232c348432bac65708780e6dc7a200046894dbe893bbc1", ".modelhub_state/submission_exclusions.jsonl": "221be895a524330815b3c5124450b33c94b5f1e68169030c73684bf675d06ec7", ".modelhub_state/worker_crashes.jsonl": "a494412048eca6dce83e7284303a6b4b56a445c1274ac201ab8723c739a14f23", - "ledger/submissions.jsonl": "e7cd37286d7fe191aaac996d5e2ce8da13c2efc6c5185bcfda80b6f828b7fc9b", - "outcomes/submissions.jsonl": "91f0c0578fdf97629a4c29c52c6395ce7671981bc39f8fafe67a9c0e536c96fd" + "ledger/submissions.jsonl": "6de86b3b8c9fda2585cd0f84bd184845933ef8cab98c1d69a0bf6a8bded3049b", + "outcomes/submissions.jsonl": "d5af1b1211c54c3e20bd2240bc8d3f8810838c779943feb5a37bb5ad2b17e22b" }, - "generation": 10138, - "phase": "intent", + "generation": 10139, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-09-20T03:40:35.053731+00:00", + "updatedAt": "2026-09-20T03:40:44.735199+00:00", "writerId": "f67e4ec113c04968a9d9484fb8e36bd4" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 73b39f48d9..42563ee651 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -802,3 +802,18 @@ {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "modelProfile": {"architectures": ["MuseGlimmerForConditionalGeneration"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21407235494, "estimatedRequiredGiB": 23.956, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "muse_glimmer", "modelscopeFileSize": 21435726263, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5792290816, "modelscopeTags": ["license:apache-2.0", "model_type:muse_glimmer", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:muse_glimmer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21435726263}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:30:31.141968+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969818", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "whcl412/mlx-LycheeAI-coder-1.7b", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 968080210, "estimatedRequiredGiB": 1.095, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 979581804, "modelscopeLicense": "apache-2.0", "modelscopeParams": 268944384, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:qwen3", "custom_tag:coder", "custom_tag:lora", "custom_tag:code", "custom_tag:lychee", "custom_tag:finetune", "custom_tag:multilingual"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 979581804}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:30:31.153489+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969817", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 951093016, "estimatedRequiredGiB": 1.068, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 955963132, "modelscopeLicense": "other", "modelscopeParams": 256113408, "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, "repositoryOnDiskBytes": 955963132}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:35:13.265606+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969892", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "neuralmagic/Meta-Llama-3-8B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084013360, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093325202, "modelscopeLicense": "llama3", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093325202}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:40:37.351352+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969964", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "neuralmagic/Qwen2-7B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8708787584, "estimatedRequiredGiB": 9.746, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 8720442075, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7615616512, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8720442075}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:40:37.293456+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969956", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-8B-A1B", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16936006912, "estimatedRequiredGiB": 18.948, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 16953948786, "modelscopeLicense": "other", "modelscopeParams": 8467856832, "modelscopeTags": ["license:other", "model_type:lfm2_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16953948786}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:40:37.353529+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969966", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9081287016, "estimatedRequiredGiB": 10.159, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9090504850, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9090504850}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:40:37.335603+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969955", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "neuralmagic/gemma-2-2b-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6746735136, "estimatedRequiredGiB": 7.565, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 6768615496, "modelscopeLicense": "gemma", "modelscopeParams": 3204165888, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6768615496}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:40:37.347716+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969963", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "neuralmagic/SmolLM-135M-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 219850592, "estimatedRequiredGiB": 0.249, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 223236742, "modelscopeLicense": "apache-2.0", "modelscopeParams": 162826560, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 223236742}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:40:37.349301+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969958", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w4a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2263018168, "estimatedRequiredGiB": 2.532, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 2265562651, "modelscopeLicense": "llama2", "modelscopeParams": 3821079552, "modelscopeTags": ["license:llama2", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2265562651}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:40:37.355419+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969959", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7686303632, "estimatedRequiredGiB": 8.592, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 7688299781, "modelscopeLicense": "llama2", "modelscopeParams": 13960238080, "modelscopeTags": ["license:llama2", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7688299781}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:40:37.357907+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969965", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/starcoder2-7b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7857298896, "estimatedRequiredGiB": 8.785, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "2026-09-20T03:40:37.343922+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969961", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14289052464, "estimatedRequiredGiB": 15.972, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 14291553638, "modelscopeLicense": "mit", "modelscopeParams": 13960238080, "modelscopeTags": ["license:mit", "model_type:phi3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14291553638}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:40:37.340106+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969960", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 658540250, "estimatedRequiredGiB": 0.741, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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, "repositoryOnDiskBytes": 663410366}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:40:37.346146+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969957", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "modelProfile": {"architectures": ["MistralForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8308282608, "estimatedRequiredGiB": 9.319, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral", "modelscopeFileSize": 8338221588, "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": 8338221588}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:40:37.342058+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969962", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "RedHatAI/starcoder2-15b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785269848, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788663591, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "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": 17788663591}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:40:44.501444+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969969", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "RedHatAI/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "f49713b9fe8e3e7683ab2722544c85a44993bcd72b9421c1599f634e68b3a2f7", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 504052632, "estimatedRequiredGiB": 0.567, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 507443052, "modelscopeLicense": "apache-2.0", "modelscopeParams": 409007040, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 507443052}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:40:44.505215+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969967", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-2.6B", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5394427456, "estimatedRequiredGiB": 6.049, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 5412393192, "modelscopeLicense": "other", "modelscopeParams": 2697198592, "modelscopeTags": ["license:other", "model_type:lfm2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5412393192}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:40:44.507984+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969968", "taskType": "text-generation", "verifyResult": null}