logo

InferX AI Function Platform (Lambda Function for Inference)

    --   Serve tens models in one box with ultra-fast (<2 sec) cold start (contact: support@inferx.net)

Pods

tenant namespace pod name state Node name Req Gpu Count Req Gpu vRam Type Standby allocated GPU vRam (MB) allocated GPU Slots
gpu pageable pinned
public Qwen public/Qwen/Qwen2.5-1.5B/128/920 Ready node3 1 8000 MB Restore Blob : 7588 MB Blob : 1314 MB Blob : 7168 MB 8192 {'1': {'contextCnt': 1, 'slotCnt': 32}}
public Qwen public/Qwen/Qwen2.5-7B-Instruct-1M/138/963 Standby node3 2 13800 MB Restore Blob : 23446 MB Blob : 1570 MB Blob : 14336 MB 0 {}
public Qwen public/Qwen/Qwen2.5-7B-Instruct-GPTQ-Int8/126/965 Standby node3 1 13500 MB Restore Blob : 13438 MB Blob : 1310 MB Blob : 7168 MB 0 {}
public Qwen public/Qwen/Qwen2.5-Coder-1.5B-Instruct/121/923 Standby node3 1 7500 MB Restore Blob : 7162 MB Blob : 1310 MB Blob : 7168 MB 0 {}
public Qwen public/Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int8/124/966 Standby node3 2 13800 MB Restore Blob : 23480 MB Blob : 1666 MB Blob : 12288 MB 0 {}
public Qwen public/Qwen/Qwen2.5-Coder-3B/119/925 Standby node3 1 13800 MB Restore Blob : 12790 MB Blob : 1310 MB Blob : 4608 MB 0 {}
public Qwen public/Qwen/Qwen2.5-Coder-7B-Instruct/117/926 Standby node3 2 13800 MB Restore Blob : 23458 MB Blob : 1570 MB Blob : 14336 MB 0 {}
public Qwen public/Qwen/Qwen2.5-Math-1.5B-Instruct/130/927 Standby node3 1 7000 MB Restore Blob : 6664 MB Blob : 1330 MB Blob : 7168 MB 0 {}
public Qwen public/Qwen/Qwen2.5-Math-1.5B/132/928 Ready node3 1 8000 MB Restore Blob : 7620 MB Blob : 1314 MB Blob : 7168 MB 8192 {'0': {'contextCnt': 1, 'slotCnt': 32}}
public Qwen public/Qwen/Qwen2.5-Math-7B-Instruct/134/929 Standby node3 2 13800 MB Restore Blob : 23438 MB Blob : 1570 MB Blob : 14336 MB 0 {}
public Qwen public/Qwen/Qwen2.5-Math-7B/136/930 Standby node3 2 13800 MB Restore Blob : 23438 MB Blob : 1594 MB Blob : 14336 MB 0 {}