Yi amfani da siffofin AI daga NVIDIA Tesla P40 (24 GB VRAM, Pascal architecture): LLMs, siffofin hoton da sauran hasashen. Masu ba da sabis na GPU ba su da iyaka; tuntuɓi mu don a sanar da mu idan sun kasance.
$ pip install vllm && vllm serve meta-llama/Llama-3-8B-Instruct
# Umarnin shigar da misali
AI inference yana tafiyar da nau'ikan da aka koyar don samar da hasashe. Mai ba da sabis na inference na GPU yana samar da kayan aiki na NVIDIA don ba da nau'ikan da ke da saurin sauka da kuma saurin gudu.
An wuce GPU zuwa mai ba da sabis ɗinka kawai, don haka ba'a shafar damuwa da ayyukan GPU na sauran masu amfani da shi ba.
Yi amfani da Ollama, llama.cpp, Triton ko kuma API ɗinka. Wasu frameworks, kamar vLLM, suna buƙatar GPUs masu sabon salo fiye da Pascal P40.
Yi amfani da wasu masu ba da sabis a bayan mai daidaita nauyinka idan GPU guda bai isa ba.
Ku bãyar da wani misalin girman tsawo guda ko wasu manya-manyan.
AI Inference zai iya amfani da NVIDIA GPU don saurin aiki. VPS.org GPU servers are not available to order yet; contact us to hear when they are. AI Inference is a general GPU-accelerated workload. Make sure your software has CUDA support and that your driver / runtime versions match the workload requirements for AI Inference.
An kasa samun masu ba da sabis na GPU don a umarce su. A yau zaka iya tafiyar da AI Inference akan wani shirin CPU na yau da kullum, inda zai yi aiki da sauri fiye da a kan GPU: SSH cikin kuma ka yi tafiyar da pip install vllm && vllm serve meta-llama/Llama-3-8B-Instruct.
Buƙatun VRAM ga AI Inference suna dogara kan nau'in da girman ƙungiya; duba takardun aikin shirin domin ƙididdiga na yanzu.
Za'a wallafa farashin GPU idan za'a iya umarnin masu ba da sabis na GPU. Ka tuntuɓi mu idan kana so ka ji lokacin da wannan ya faru.
Yanzu, duk mai ba da sabis na VPS.org yana da damar shiga mai amfani da shi, don haka zaka iya tafiyar da wasu kayan aiki tare da AI Inference cikin RAM da ajiyar mai ba da sabis.
Every VPS.org server comes with full root SSH access, so you can install drivers, libraries and AI Inference however you need.
Ba. Babu mai ba da sabis da ya zo da wani CUDA runtime ko NVIDIA mai sarrafa da aka shigar da shi a gaba, kuma masu ba da sabis na GPU ba su da sauki a umarce su ba har yanzu. Za ka iya shigar da sifofin da AI Inference ke bukata kai tsaye.
Ya. VPS.org servers are persistent virtual machines, not ephemeral instances: AI Inference models, configurations and data stay on the server's SSD storage until you delete them.
Ka riƙe bayanan aiki a kan SSD na mai ba da sabis domin samun damar sauri yayin da ake tafiyar da AI Inference, kuma ka kwafe artifacts da aka gama (matsaloli, shekaru, embeddings) zuwa ajiyar waje VPS.org; snapshots da backups suna zama a kan ƙungiya mai ajiyar guda.
Za ka iya canza kowace masarauta VPS.org zuwa wani shirin da ya fi girma daga fanel na kulawa; sake girman zai sake fara shi kuma shigarwarka ta AI Inference za ta yi ta. Masarautar GPU ba ta da sauki ba har yanzu.
Yes. Backups are a paid add-on (daily +30% of the plan price, kept 7 days; weekly +20%, kept 28 days) and snapshots are free, which is useful before long AI Inference runs. Both stay on the same storage cluster as the server.
Ka tuntubi goyon baya cikin kwanaki 30 na farkon siyarka don neman dawo da kuɗi. Ba a sayar da masu watsa shirye-shiryen GPU ba har yanzu, don haka babu umarnin GPU da aka haɗa.
GPU na da iyakacin ƙarfin aiki. Ka gaya mana game da nauyin aikinka kuma za mu amsa da damar da farashin.