diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 164b5e2405..261d996a82 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -2293,7 +2293,7 @@ {"batchId": "503ab91729b946c6883bad0ad4dfce12", "completedAt": "2026-09-21T20:22:32.936762+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T20:22:30.126232+00:00", "framework": "vllm_tokenizer_patch", "intentId": "b6843413edab4f2687a7fddcb3c23d3f", "lastModified": "2026-09-21T20:13:14+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-kda-kernel-64-v2", "reason": null, "reconciledAt": "2026-09-21T20:26:17.638058+00:00", "repoId": "nkkbr/Mini-K3-1H-kda-kernel-64-v2", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "5006826", "taskType": "text-generation"} {"batchId": "503ab91729b946c6883bad0ad4dfce12", "completedAt": "2026-09-21T20:22:32.936782+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T20:22:30.126341+00:00", "framework": "vllm_fix_tokenizer", "intentId": "cbe9a7e9f02d4794834f4d3c89c87f3f", "lastModified": "2026-09-21T18:38:06+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attnres-standard-v1_B", "reason": null, "reconciledAt": "2026-09-21T20:26:17.636729+00:00", "repoId": "nkkbr/Mini-K3-1H-attnres-standard-v1_B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Iluvatar_bi-150", "taskId": "5006825", "taskType": "text-generation"} {"batchId": "de7be1887fb943db80077113aab19f7d", "completedAt": "2026-09-21T20:24:44.320851+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T20:24:42.392100+00:00", "framework": "vllm", "intentId": "deca3187fb0f43a19fb934467119fe0d", "lastModified": "2026-09-21T18:44:33+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attnres-block6-v1_C", "reason": null, "reconciledAt": "2026-09-21T20:26:17.638904+00:00", "repoId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Mthreads_s4000", "taskId": "5006850", "taskType": "text-generation"} -{"batchId": "6e1c6ac73c394636a6a10fe3663125fa", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T20:26:43.709790+00:00", "framework": "vllm", "intentId": "d3d3f1c1b5d34ddfbed9398607656dbe", "lastModified": "2026-09-21T18:45:44+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g16-v2_B", "repoId": "nkkbr/Mini-K3-1H-decay-g16-v2_B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Mthreads_s4000", "taskType": "text-generation"} +{"batchId": "6e1c6ac73c394636a6a10fe3663125fa", "completedAt": "2026-09-21T20:26:44.867873+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T20:26:43.709790+00:00", "framework": "vllm", "intentId": "d3d3f1c1b5d34ddfbed9398607656dbe", "lastModified": "2026-09-21T18:45:44+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g16-v2_B", "reason": null, "repoId": "nkkbr/Mini-K3-1H-decay-g16-v2_B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Mthreads_s4000", "taskId": "5006868", "taskType": "text-generation"} {"batchId": "f8d3f1991720478ea905a5ecf7d43601", "completedAt": "2026-09-21T19:05:00.691781+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:00:55.137064+00:00", "framework": "vllm", "intentId": "64b834dd640742a0b32535bde02b94ad", "repoId": "CohereLabs/tiny-aya-base-32K", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "f8d3f1991720478ea905a5ecf7d43601", "completedAt": "2026-09-21T19:05:00.691779+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:00:55.137007+00:00", "framework": "vllm", "intentId": "d6229ef4ac9942078baa35e312133d9d", "repoId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "f8d3f1991720478ea905a5ecf7d43601", "completedAt": "2026-09-21T19:05:00.691776+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:00:55.136949+00:00", "framework": "vllm", "intentId": "cff6b666a842431faf928f94c2086fdf", "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"} diff --git a/.modelhub_state/routing_intelligence.json b/.modelhub_state/routing_intelligence.json index f76d889b99..04141eae10 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,6 +1,6 @@ { "acceptedByCategory": { - "unified_success_first": 2432 + "unified_success_first": 2433 }, "acceptedByRoute": { "text-generation|Ascend_910-b3|llamacpp": 17, @@ -30,7 +30,7 @@ "text-generation|Kunlunxin_p-800|vllm_tokenizer_patch": 96, "text-generation|MetaX_c-500|vllm": 105, "text-generation|Mthreads_s4000|llamacpp": 17, - "text-generation|Mthreads_s4000|vllm": 111, + "text-generation|Mthreads_s4000|vllm": 112, "text-generation|Sunrise_pt-200-x1|vllm": 85, "text-generation|Sunrise_pt-200-x1|vllm_fix_tokenizer": 94, "text-generation|Vastai_va16|vllm_fix_tokenizer": 75, @@ -38,8 +38,8 @@ "text-generation|hygon_k100-ai|vllm": 26, "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 134 }, - "acceptedSinceRefresh": 2432, - "acceptedTotal": 2432, - "generatedAt": "2026-09-21T20:24:44.254689+00:00", + "acceptedSinceRefresh": 2433, + "acceptedTotal": 2433, + "generatedAt": "2026-09-21T20:26:44.797873+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index fc31071121..768f5cb736 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -1265,3 +1265,4 @@ {"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": "transformers", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-quantized.w8a16", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a16", "submitTime": "2026-09-21T18:32:49.780633+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5005549", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-150"} +{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g16-v2_B", "modelId": "nkkbr/Mini-K3-1H-decay-g16-v2_B", "submitTime": "2026-09-21T20:26:44.746980+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5006868", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"} diff --git a/manifest.json b/manifest.json index c1724f3095..2fe942df39 100644 --- a/manifest.json +++ b/manifest.json @@ -10,16 +10,16 @@ ".modelhub_state/queue_cleanup_latest.json": "f93bde2de8f7cc7073f34b5456a3df43c8f54023eacfce210dc11e227efd469c", ".modelhub_state/recent_outcomes.jsonl": "9e2a4dc46246785df8dffcbd4b6aea5cc0b32794af784e60d3a212af041c91c6", ".modelhub_state/recovery_active_tasks.jsonl": "386d3c318d62458eb5de433ac8fb9685c66eabd18e47256bfe4d2d0de5670263", - ".modelhub_state/recovery_intents.jsonl": "ef9bb330b642f8286731370c25ab290492bb5ad8dd7cc8cb73c2c83b18466c8c", - ".modelhub_state/routing_intelligence.json": "3f027d0d5eb0e251cdb9b7b696e12c6251dccf7154fa1ca529a628fbbb181da9", + ".modelhub_state/recovery_intents.jsonl": "c31095f191238443ad4b1643e69c9b910c9a4cdeea91aeb22c1a6fa4a1cd0d95", + ".modelhub_state/routing_intelligence.json": "466c8b45787bdad3d1078738cdda1cf050eb4985516d6eec37a7f4e67bb74848", ".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989", ".modelhub_state/worker_crashes.jsonl": "07505b69e0b050da5f90f8b046a3069d3e1ca2574ca39896bc7d8a66293167f7", - "ledger/submissions.jsonl": "2211bd0acf2530e0894623c18483cc60b0a011768c99712bbb8883eac038f9c8", - "outcomes/submissions.jsonl": "c9994ebf1e8000fa76f64f717504261922796799528cbdfc50098e88ffea2c3e" + "ledger/submissions.jsonl": "6c2b864965d49bad75ee3f1937fbd1e619caefefb7f8f7b6882f5d573389d6f8", + "outcomes/submissions.jsonl": "0c0a2fb2cd5d8111c82c5e7e3fe43e850976aa8e1b38e150d65df8bc2b261bc8" }, - "generation": 11707, - "phase": "intent", + "generation": 11708, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-09-21T20:26:43.911536+00:00", + "updatedAt": "2026-09-21T20:26:44.998482+00:00", "writerId": "8b35139af6674067a339a670222d4b67" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 10d210dc56..66697f9030 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -1208,3 +1208,4 @@ {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-kda-kernel-64-v2", "modelProfile": {"architectures": [], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2044205392, "estimatedRequiredGiB": 2.469, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2168994941, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2209448692}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T20:22:32.043790+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5006826", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-attnres-standard-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034135144, "estimatedRequiredGiB": 2.282, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042280856}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T20:22:32.047761+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5006825", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251896, "estimatedRequiredGiB": 2.283, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042626482}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T20:24:44.145520+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5006850", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-decay-g16-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2031106928, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039475672}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T20:26:44.746980+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5006868", "taskType": "text-generation", "verifyResult": null}