I-Multi-Instance GPU Partitioning
I-Multi-Instance GPU (MIG) ubuchwepheshe be-NVIDIA obusika i-GPU eyodwa ebonakalayo ibe izingxenye eziningi ezihlukene zehadiwe.
Uhlolojikelele
It matters because it lets one expensive accelerator serve many small workloads at once without them interfering with each other.
I-Deep Dive
Yethulwe nge-NVIDIA A100 (Ampere) futhi yaqhubeka ku-H100 kanye nama-GPU amasha esikhungo sedatha, i-MIG iqopha i-GPU ibe yizimo ezizimele ezingafika kweziyisikhombisa. Ngokungafani nokusika isikhathi kwesofthiwe, i-MIG inikeza ukuhlukaniswa kwehadiwe kwangempela: isibonelo ngasinye sithola ama-multiprocessors aso azinikele (ama-SMs), izingcezu zenqolobane ye-L2, izilawuli zememori, nocezu olumisiwe lwenkumbulo yomkhawulokudonsa ophezulu. I-A100 ene-40GB ingahlukaniswa ibe yizimo ezingu-5GB eziyisikhombisa, noma ezimbalwa ezinkulu. Ingxenye ngayinye iziphatha njenge-GPU encane ezimele, ngakho-ke umsebenzi onomsindo noma ophahlazekayo esimweni esisodwa awukwazi ukulamba noma ukonakalisa esinye. Le khwalithi yesevisi eqinisekisiwe yenza i-MIG ibe ilungele ukukhonza okucatshangwayo, amaqoqo abaqashile abaningi, kanye nezindawo zokuthuthuka lapho abasebenzisi abaningi babelana ngekhadi elilodwa.
I-Technical Insight
I-MIG isebenza ngokufaka isango kubha yangaphakathi ye-GPU ukuze isibonelo ngasinye sibe nendlela eqondile eya kucezu lwaso lwememori nama-SM. I-NVIDIA ichaza amaphrofayili njengamafrakshini afana no-1g.5gb (ucezu lwekhompyutha olulodwa, 5GB) kufika ku-7g.40gb. I-GPU Instance igcina inkumbulo nama-SM; ngaphakathi kwayo i-Compute Instance ihlukanisa ama-SM ngokuqhubekayo. Ngoba ukwahlukanisa kuphoqelelwe ihadiwe, amaphutha, amaphutha e-ECC, kanye nomkhawulokudonsa wememori uhlala esimeni esisodwa.
I-Strategic Impact
Izindleko kanye nesabelomali
Izinqumo zezakhiwo ziqhuba ukusebenza kanye nezindleko zokusebenza iminyaka.
Izinqumo ezicacile
Imfundo yobuchwepheshe isiza amaqembu ukuthi akhethe isitaki esifanele, hhayi nje esisha.
Ukulawulwa kwekhwalithi
Izinketho ezingcono zobunjiniyela zinciphisa izehlakalo ezinokwethenjelwa ekukhiqizeni.
Ikusasa Le-Multi-Instance GPU Partitioning
Njengoba ama-GPU ekhula aze afike ku-80GB, 141GB, nangale kwalokho, ukwahlukanisa kuba kukhanga kakhulu ngoba amamodeli ngamanye awavamile ukudinga ikhadi eliphelele ukuze aqondiswe. Lindela i-Kubernetes eqinile kanye nokuhlanganiswa kwamafu, ukwahlukanisa okuguquguqukayo ngaphandle kokukhipha i-node, kanye namaphrofayili ahlotshiswe kahle. Abathengisi abaqhudelanayo baphishekela ukwenziwa okufanayo kwe-GPU yesitayela se-SR-IOV, futhi amapulatifomu angenasiphakeli ancike kakhulu ekwahlukaniseni ukupakisha amamodeli amaningi aminyene futhi asike imfucuza engasebenzi.
Ukuqaliswa Komhlaba Wangempela
Umhlinzeki wamafu uhlukanisa i-A100 eyodwa ibe yizimo eziyisikhombisa ukuze amakhasimende ayisikhombisa lilinye athole ucezu lwe-GPU oluqinisekisiwe, oluhlukanisiwe ukuze kucatshangwe.
Iqoqo locwaningo lwasenyuvesi linikeza umfundi ngamunye we-PhD isibonelo se-MIG esingu-10GB sokwenza i-prototyping esikhundleni sokuthatha wonke amakhadi.
Isevisi ye-inference ipakisha amamodeli ambalwa olimi amancane kanye nombono ku-H100 eyodwa, ngalinye lisendaweni yalo enokubambezeleka okungabikezelwa.
Iqoqo le-Kubernetes likhangisa izimo ze-MIG njengezinsiza ezihlelekayo ukuze ama-pods acele i-'nvidia.com/mig-1g.5gb' njenganoma iyiphi enye insiza.
Izingozi & Guardrails
Ukuthuthukisa ibhentshimakhi eyodwa kungafihla ubuthakathaka obubanzi besistimu.
Izindleko zengqalasizinda nezokulungisa zivame ukubukelwa phansi.
Izikhala zokuphepha nokubonakala zingakhula njengoba izinhlelo ziba nzima kakhulu.
Ukuqalisa Umhlahlandlela
Chaza ukubambezeleka, ikhwalithi, nezindleko ezihlosiwe ngaphambi kokuqaliswa.
Ibhentshimakhi ngaphansi komthwalo wangempela nezimo zedatha.
Ukuqapha amathuluzi amaphutha, ukukhukhuleka, nomthelela wabasebenzisi.
Lungiselela izindlela zokuhlehlisa nezigameko ngaphambi kokukala.
Qhubeka Uhlole
Free newsletter
Get the daily AI briefing
Three verified AI stories every weekday morning, written in plain English. Free forever, no ads.
One email each weekday. Unsubscribe in one click. We never sell or share your address.
Test yourself
Take the Multi-Instance GPU Partitioning quiz
Instant feedback on every answer, and a shareable certificate with a verifiable ID once you pass a course.
Support free AI education. AI Understanding is a 501(c)(3) nonprofit — no ads, no paywall, ever. Make a donation
Umhlahlandlela olandelayo
I-Multi-Task Learning
Imibuzo evame ukubuzwa
What is Multi-Instance GPU Partitioning?
I-Multi-Instance GPU (MIG) ubuchwepheshe be-NVIDIA obusika i-GPU eyodwa ebonakalayo ibe izingxenye eziningi ezihlukene zehadiwe. Kubalulekile ngoba ivumela isisheshisi esisodwa esibizayo ukuthi sisebenze imithwalo eminingi emincane ngesikhathi esisodwa ngaphandle kokuthi siphazamisane.
Iluphi uhlobo lokuzihlukanisa olunikezwa yi-MIG phakathi kwezimo?
I-MIG iphoqelela ukuhlukaniswa kwezingxenyekazi zekhompuyutha, inikezela ama-SM, izingcezu zenqolobane ye-L2, kanye nenkumbulo esimweni ngasinye ukuze imithwalo yomsebenzi ingakwazi ukuphazamisa.
Ikuphi ukwakhiwa kwe-NVIDIA eyethulwa kuyo okokuqala i-MIG?
I-MIG iqale nge-Ampere-based A100 futhi yaqhubeka kuma-H100 futhi kamuva nama-GPU esikhungo sedatha.
Ingakanani inombolo enkulu yezenzakalo i-GPU ekwazi ukuhlukaniselwa kuzo i-MIG?
I-GPU enamandla e-MIG efana ne-A100 ingahlukaniswa ibe yizimo ezizimele eziyisikhombisa.
Kuphrofayela ye-MIG efana ne-'1g.5gb', imele ini i-'5gb'?
Iphrofayela ifaka ama-comute tincetu (1g) kanye nememori enikelwe (5GB) enikezwe isibonelo.
Imuphi umsebenzi we-MIG owufanele kakhulu?
I-MIG iyakhanya lapho imisebenzi eminingi emincane, engayodwa (efana nencazelo) yabelana ngekhadi elilodwa nekhwalithi yesevisi eqinisekisiwe.