Ubuyobozi bwa tekiniki

Gutandukanya Prefill na Decode Gukora

Ubwubatsi bukora bugabanya imvugo nini yerekana urugero mubice bibiri bitandukanye - prefill na decode - ikanabikoresha kubidendezi bitandukanye bya GPU.

Incamake

Ubwubatsi bukora bugabanya imvugo nini yerekana urugero mubice bibiri bitandukanye - prefill na decode - ikanabikoresha kubidendezi bitandukanye bya GPU. Ntacyo bitwaye kuko ibyo byiciro byombi bifite ubushake buke bwibikoresho, kandi kubahatira kumashini imwe isesagura ubushobozi kandi bikababaza ubukererwe.

Gutandukanya Prefill na Decode Gukora ni tekinoroji ya tekiniki yubaka igira ingaruka kumiterere yicyitegererezo, igiciro cyibikorwa remezo, ubukererwe, no kwizerwa mubipimo.

Kwibira cyane

Iyo LLM isubije, ikora mubyiciro bibiri. Prefill isoma icyarimwe icyarimwe hanyuma yubake urufunguzo-agaciro (KV) cache; iyi nini nini, ibangikanye, kubara-guturika kuzuza ibice byimibare ya GPU. Decode noneho itanga ibimenyetso kimwekimwe, buri ntambwe isoma cache yose ya KV-yibuka-umurongo-wuzuye, uhuza-kubara. Kwiruka hamwe, prefill ndende ihagarika decode ya buriwese (umutwe-wumurongo uhagarika), kandi gukubita byombi bitera kwivanga. Gutandukana bishyira prefill kuri pisine imwe ya GPU hanyuma ukarangiza kurindi, kwimura cache cache hagati yabo hejuru yimikoranire yihuse nka NVLink cyangwa InfiniBand. Buri kidendezi cyarateguwe kandi gipimwa mu bwigenge, kunoza ibicuruzwa byiza, koroshya umurizo, no kureka ababikora bagakubita igihe-kuri-mbere-ikimenyetso-nigihe-cyo-gusohora-icyerekezo icyarimwe.

Ubushishozi

Ibyiciro byombi biratandukanye muburyo bwabo. Kuzuza ibintu byose byihutirwa muburyo bubangikanye, nuko FLOPs igipimo cyayo hamwe nuburebure bwihuse kandi ikarenza tensor cores. Decode ni autoregressive: buri kimenyetso gishya gikenera inzira imwe yimbere yongeye gusoma kashe yuzuye ya KV kuva HBM, bityo ibyinjira byinjizwa numuyoboro mugari, ntabwo ubara. Gutandukana kubikoresha mugupima, gutobora, ndetse no guhitamo kubangikanya kuri buri kidendezi, hanyuma kohereza cache cache kuva kubakozi bambere kugeza kubakozi.

Kumenyereza Byuzuye Byuzuye Byuzuye na Decode Gukora

Ubwubatsi bukora bugabanya imvugo nini yerekana urugero mubice bibiri bitandukanye - prefill na decode - ikanabikoresha kubidendezi bitandukanye bya GPU. Ntacyo bitwaye kuko ibyo byiciro byombi bifite ubushake buke bwibikoresho, kandi kubahatira kumashini imwe isesagura ubushobozi kandi bikababaza ubukererwe. Gutandukanya Prefill na Decode Gukora ni tekinoroji ya tekiniki yubaka igira ingaruka kumiterere yicyitegererezo, igiciro cyibikorwa remezo, ubukererwe, no kwizerwa mubipimo. Kugirango wubake byimbitse, fata Prefgregated Prefill na Decode Gukora nkicyitegererezo cyibikorwa, ntabwo ari ikintu kimwe: gusobanura ibyagezweho, gusobanura ibitekerezo, no gutandukanya ibyo sisitemu ishobora gukora byizewe nibisaba guca imanza zinzobere.

Mu myitozo, amakipe akomeye akoresha Prefgregated Prefill na Decode Gukora neza uburyo bwubaka, amakuru, hamwe nibikorwa remezo birwanya kwizerwa nigiciro. Bandika ibipimo ngenderwaho byerekana intsinzi, bagerageza kurwanya amakuru afatika hamwe nakazi keza, kandi bagasubiramo bashingiye kubikorwa byagaragaye ko batsinzwe aho gutsinda inshuro imwe. Aha niho imyumvire yubumenyi ihinduka mubushobozi burambye kubicuruzwa, politiki, nibikorwa.

Ibyemezo byubwubatsi bitwara imikorere nigiciro cyimikorere kumyaka. Mugihe kimwe, Guhindura igipimo kimwe gishobora guhisha intege nke za sisitemu. Uburyo bukomeye cyane ni uguhuza umuvuduko wikigereranyo hamwe na disipuline yimiyoborere: kuyobora abaderevu, gufata ibimenyetso, gutangaza ibyemezo byicyemezo, no gukomeza kuvugurura uburyo bwo kwirinda nkimyitwarire yicyitegererezo, ibyo abakoresha bategereje, nibisabwa n'amategeko bigenda bihinduka.

Ingaruka z'Ingamba

Ibyemezo byubwubatsi bitwara imikorere nigiciro cyimikorere kumyaka.

Ibyemezo byubwubatsi bitwara imikorere nigiciro cyimikorere kumyaka. Mubikorwa byujuje ubuziranenge, ibi bihindurwa mumategeko agenga imikorere, imipaka nyirubwite, hamwe n'imihango yo gusubiramo kenshi kugirango amakipe ashobore kwigirira ikizere aho gupima ibidasobanutse.

Ubuhanga bwa tekinike bufasha amakipe guhitamo umurongo ukwiye, ntabwo ari shyashya gusa.

Ubuhanga bwa tekinike bufasha amakipe guhitamo umurongo ukwiye, ntabwo ari shyashya gusa. Mubikorwa byujuje ubuziranenge, ibi bihindurwa mumategeko agenga imikorere, imipaka nyirubwite, hamwe n'imihango yo gusubiramo kenshi kugirango amakipe ashobore kwigirira ikizere aho gupima ibidasobanutse.

Guhitamo neza bya injeniyeri bigabanya ibintu byizewe mubikorwa.

Guhitamo neza bya injeniyeri bigabanya ibintu byizewe mubikorwa. Mubikorwa byujuje ubuziranenge, ibi bihindurwa mumategeko agenga imikorere, imipaka nyirubwite, hamwe n'imihango yo gusubiramo kenshi kugirango amakipe ashobore kwigirira ikizere aho gupima ibidasobanutse.

Kazoza Kutuzuye Kuzuza no Gukora Dode

Witege ko gutandukana bizaba nkibisanzwe mubikorwa. Sisitemu nka DistServe, Splitwise, na Mooncake yarayamamaye, kandi vLLM na NVIDIA Dynamo ubu ubwato butandukanye. Ubushakashatsi burimo gusunika KV-cache kwimura optimizasiyo, guhuza cache no kongera gukoresha ibyifuzo, imbaraga zo kongera kuringaniza ibipimo bya prefill / decode munsi yimodoka ihindagurika, hamwe no guhuza cyane hamwe na prefix cishing hamwe na prefill chunked prefill. Mugihe imiterere ya Windows ikura miriyoni yikimenyetso, gutandukanya ibi byiciro biba ngombwa cyane kubiciro bikoresha neza, bitinze cyane.

Gushyira mu bikorwa Isi

Ikiganiro cyunganira kuganira inzira ndende yerekana compte-iremereye ya prefill cluster, hanyuma imigezi isubiza uhereye kumyibutsa-optimiz ya decode cluster kugirango ukomeze kwandika neza.

NVIDIA Dynamo na vLLM bareke abakoresha bashire prefill zitandukanye hamwe na decode yitsinda ryabakozi kugirango guturika kwigihe kirekire ntibishobora guhagarika ibisekuru bikomeza.

Mooncake (ikoreshwa na Kimi ya Moonshot AI) itandukanya prefill na decode kandi ikongeramo pisine yagabanijwe ya KV-cache kugirango igabanye inshuro nyinshi kubipimo.

Serivisi yo kurangiza-kode yegurira pisine ntoya ya progaramu ya progaramu ngufi na pisine nini ya decode, kubera ko ikiguzi kinini kiva mugutanga ibimenyetso byinshi bisohoka.

Uburyo bwo Gushyira mu bikorwa

Gutandukanya Prefill na Decode Gukorera mubikorwa

Ikiganiro cyunganira kuganira inzira ndende yerekana compte-iremereye ya prefill cluster, hanyuma imigezi isubiza uhereye kumyibutsa-optimiz ya decode cluster kugirango ukomeze kwandika neza.

Ikiganiro cyunganira kuganira inzira ndende isaba compte-iremereye ya prefill cluster, hanyuma imigezi isubiza uhereye kumyibutsa-yashizwemo na decode cluster kugirango ukomeze kwandika ubukererwe bworoshye Amakipe mubisanzwe abona ibisubizo byiza mugihe asobanura ibipimo byimbere imbere, agakomeza inzira yo kuzamuka kwabantu kubibazo byimbere, kandi akurikirana inyungu zibyara umusaruro nibiciro byigihe.

Gutandukanya Prefill na Decode Gukorera mubikorwa

NVIDIA Dynamo na vLLM bareke abakoresha bashire prefill zitandukanye hamwe na decode yitsinda ryabakozi kugirango guturika kwigihe kirekire ntibishobora guhagarika ibisekuru bikomeza.

NVIDIA Dynamo na vLLM reka abashinzwe gukoresha amatsinda atandukanye ya prefill na decode yitsinda ryabakozi kugirango guturika kwigihe kirekire ntibishobora guhagarika ibisekuru bikomeza Amakipe akunze kubona umusaruro ushimishije mugihe asobanura ibipimo ngenderwaho byimbere imbere, agakomeza inzira yo kuzamura abantu kubibazo bikurikirana, kandi agakurikirana inyungu zumusaruro hamwe nibiciro byamakosa mugihe runaka.

Gutandukanya Prefill na Decode Gukorera mubikorwa

Mooncake (ikoreshwa na Kimi ya Moonshot AI) itandukanya prefill na decode kandi ikongeramo pisine yagabanijwe ya KV-cache kugirango igabanye inshuro nyinshi kubipimo.

Mooncake (ikoreshwa na Kimi ya Moonshot AI) itandukanya prefill na decode kandi ikongeramo pisine yagabanijwe ya KV-cache kugirango igabanye ibihembo byihuse kubipimo Amakipe ubusanzwe abona ibisubizo byiza iyo asobanuye ibipimo ngenderwaho byimbere, agakomeza inzira yo kuzamuka kwabantu kubibazo byimanza, kandi akurikirana inyungu zibyara umusaruro nibiciro byigihe.

Gutandukanya Prefill na Decode Gukorera mubikorwa

Serivisi yo kurangiza-kode yegurira pisine ntoya ya progaramu ya progaramu ngufi na pisine nini ya decode, kubera ko ikiguzi kinini kiva mugutanga ibimenyetso byinshi bisohoka.

Serivisi yo kurangiza-kode itanga pisine ntoya ya progaramu ya progaramu ngufi na pisine nini ya decode, kubera ko ikiguzi kinini kiva mugukwirakwiza ibimenyetso byinshi bisohoka Amakipe ubusanzwe abona ibisubizo byiza iyo asobanuye ibipimo byujuje ubuziranenge imbere, agakomeza inzira yo kuzamura abantu kubibazo, kandi akurikirana inyungu zibyara umusaruro nibiciro byigihe.

Ingaruka & Kurinda

!

Gutezimbere igipimo kimwe gishobora guhisha intege nke za sisitemu.

!

Ibikorwa Remezo no kubungabunga akenshi usanga bidahabwa agaciro.

!

Icyuho cyumutekano no kwitegereza birashobora kwiyongera uko sisitemu igenda igorana.

Igishushanyo mbonera

1

Sobanura ubukererwe, ubuziranenge, nigiciro cyibiciro mbere yo kubishyira mubikorwa.

Sobanura ubukererwe, ubuziranenge, nigiciro cyibiciro mbere yo kubishyira mubikorwa. Fata buri ntambwe nk irembo ryibimenyetso: niba ibipimo bitujujwe, hagarika kuzenguruka, funga icyuho, hanyuma noneho wagure imikoreshereze.

2

Ibipimo byerekana umutwaro ufatika hamwe namakuru yimiterere.

Ibipimo byerekana umutwaro ufatika hamwe namakuru yimiterere. Fata buri ntambwe nk irembo ryibimenyetso: niba ibipimo bitujujwe, hagarika kuzenguruka, funga icyuho, hanyuma noneho wagure imikoreshereze.

3

Gukurikirana ibikoresho kubikosa, drift, ningaruka zabakoresha.

Gukurikirana ibikoresho kubikosa, drift, ningaruka zabakoresha. Fata buri ntambwe nk irembo ryibimenyetso: niba ibipimo bitujujwe, hagarika kuzenguruka, funga icyuho, hanyuma noneho wagure imikoreshereze.

4

Tegura inzira yo gusubiza ibyabaye mbere yo gupima.

Tegura inzira yo gusubiza ibyabaye mbere yo gupima. Fata buri ntambwe nk irembo ryibimenyetso: niba ibipimo bitujujwe, hagarika kuzenguruka, funga icyuho, hanyuma noneho wagure imikoreshereze.

Komeza Ubushakashatsi