Ururimi AI

KV Cache

Ubwihisho bwa KV bubika urufunguzo nagaciro kerekana impinduka transformateur yamaze kubara kubimenyetso byabanje, ntabwo rero igomba kubisubiramo kuri buri jambo rishya ritanga.

Incamake

Ubwihisho bwa KV bubika urufunguzo nagaciro kerekana impinduka transformateur yamaze kubara kubimenyetso byabanje, ntabwo rero igomba kubisubiramo kuri buri jambo rishya ritanga. Ninimpamvu imwe nini ituma inyandiko yihuta - kandi ikintu nyamukuru urya ububiko bwa GPU mugihe cyibiganiro birebire.

KV Cache ni igice cyururimi-AI stack ikoreshwa mugusoma, kubyara, gutondekanya, no guhindura inyandiko nimvugo murwego.

Kwibira cyane

Abahinduzi batanga inyandiko ikimenyetso kimwe icyarimwe, kandi buri kimenyetso gishya cyitonderwa kigomba kugereranya na buri kimenyetso kibanziriza. Uburyo bwo kwitondera buhindura buri kimenyetso mubibazo, urufunguzo, nagaciro kerekana. Hatabayeho gufunga, kubyara ikimenyetso 1.000 bisobanura kubara urufunguzo nagaciro kubimenyetso 999 byambere kuri buri ntambwe - umurimo wa quadratic, usesagura. Ubwihisho bwa KV bubika urufunguzo nagaciro byagaciro nyuma yo kubarwa bwa mbere no kubikoresha, buri ntambwe nshya rero ibara ibice gusa kubimenyetso bishya kandi ikitabira hejuru ya cache yabitswe. Ibi bigabanuka kuri buri kimenyetso kuva gupima hamwe nuburebure bwikurikiranya kugeza hafi. Ubucuruzi-bwibukwa ni kwibuka: cache ikura neza hamwe nuburebure bwimiterere, umubare wibice, hamwe nimitwe yitabwaho, akenshi biba byiganjemo abaguzi bibuka mugihe kirekire.

Ubushishozi

Mugihe cya 'prefill' icyiciro icyitegererezo gitunganya ikibazo cyose kandi cyuzuza cache; mugihe cya 'decode' yongeraho ikimenyetso kimwe K / V kuri buri ntambwe hanyuma ikongera. Ingano yubunini bwa 2 (K na V) × ibice × imitwe × umutwe_dim × ikurikiranye_uburebure × icyiciro, muburyo bwatoranijwe. Kugirango ukemure ibi, moderi zigezweho zikoresha amatsinda-kubaza cyangwa kubaza ibibazo byinshi kugirango dusangire urufunguzo / indangagaciro mumitwe, hamwe na sisitemu nka vLLM ikoresha PagedIbyitonderwa kugirango igabanye cache mubice bidahuza, guca ibice hamwe n imyanda.

Kumenya KV

Ubwihisho bwa KV bubika urufunguzo nagaciro kerekana impinduka transformateur yamaze kubara kubimenyetso byabanje, ntabwo rero igomba kubisubiramo kuri buri jambo rishya ritanga. Ninimpamvu imwe nini ituma inyandiko yihuta - kandi ikintu nyamukuru urya ububiko bwa GPU mugihe cyibiganiro birebire. KV Cache ni igice cyururimi-AI stack ikoreshwa mugusoma, kubyara, gutondekanya, no guhindura inyandiko nimvugo murwego. Kugirango wubake byimbitse, fata KV Cache nkicyitegererezo gikora, ntabwo ari ikintu kimwe: gusobanura ibyagezweho, gusobanura ibitekerezo, no gutandukanya ibyo sisitemu ishobora gukora byizewe nibisaba guca imanza zinzobere.

Mu myitozo, amakipe akomeye akoresha KV Cache igishushanyo mbonera, kugarura, no gusubiramo imirongo nka sisitemu imwe y'itumanaho ihuriweho. 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.

Ururimi rwakazi rushobora kugenda byihuse nta gutamba guhuzagurika. Mugihe kimwe, ibintu bya Hallucinated birashobora kwinjiza bucece raporo, gushyigikira imigendekere, cyangwa ibisubizo byubushakashatsi. 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

Ururimi rwakazi rushobora kugenda byihuse nta gutamba guhuzagurika.

Ururimi rwakazi rushobora kugenda byihuse nta gutamba guhuzagurika. Mubikorwa byujuje ubuziranenge, ibi bihindurwa mumategeko agenga imikorere, imipaka nyirubwite, hamwe n'imihango yo gusubiramo kenshi kugirango amakipe ashobore kwigirira ikizere aho gupima ibidasobanutse.

Yagura uburyo bwindimi nuburyo bwo gutumanaho.

Yagura uburyo bwindimi nuburyo bwo gutumanaho. Mubikorwa byujuje ubuziranenge, ibi bihindurwa mumategeko agenga imikorere, imipaka nyirubwite, hamwe n'imihango yo gusubiramo kenshi kugirango amakipe ashobore kwigirira ikizere aho gupima ibidasobanutse.

Amakipe arashobora kumara umwanya munini murubanza mugihe automatike ikora gusubiramo.

Amakipe arashobora kumara umwanya munini murubanza mugihe automatike ikora gusubiramo. 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 ka KV Cache

Mugihe imiterere ya Windows irambuye mu bihumbi magana, ibimenyetso bya KV bihinduka icyuho cyo hagati, bityo guhanga udushya birakaze: kubara cache kugeza kuri 8 cyangwa 4 bits, politiki yo kwirukana igabanya ibimenyetso bidafite akamaro gake, kugabana ibyifuzo mbere yo kugabana, no gupakurura CPU cyangwa disiki. Imyubakire ihindagurika nkimitwe myinshi yihishe yitonze ikanda cache ubwayo. Tegereza gukomeza gufatanya gushushanya ibitekerezo hamwe na sisitemu yo kwibuka igamije gukora ibintu birebire cyane bihendutse kandi byinjira cyane.

Gushyira mu bikorwa Isi

Kwihutisha chatbot isubiza ukoresheje urufunguzo rwihishwa / indangagaciro kuva mumateka y'ibiganiro aho kuyisubiramo buri gihe.

Prefix cishing isangira cache kumurongo muremure wa sisitemu kubakoresha benshi, kugabanya ibiciro nubukererwe.

vLLM's PagedIcyifuzo cyo gucunga KV cache mubice kugirango ukore ibyifuzo byinshi bihurira kuri GPU imwe neza.

Kugabanya ubwihisho bwa KV kugirango ugabanye neza kugirango uhuze umwanya muremure mububiko buke bwa GPU.

Uburyo bwo Gushyira mu bikorwa

KV Cache mubikorwa

Kwihutisha chatbot isubiza ukoresheje urufunguzo rwihishwa / indangagaciro kuva mumateka y'ibiganiro aho kuyisubiramo buri gihe.

Kwihutisha ibisubizo bya chatbot ukoresheje urufunguzo rwihishwa / indangagaciro kuva mumateka y'ibiganiro aho kubisubiramo buri cyiciro Amakipe akunze kubona ibisubizo byiza iyo asobanuye ibipimo byujuje ubuziranenge imbere, agakomeza inzira yo kuzamura abantu kubibazo, kandi akurikirana inyungu zibyara umusaruro hamwe nibiciro byamakosa mugihe runaka.

KV Cache mubikorwa

Prefix cishing isangira cache kumurongo muremure wa sisitemu kubakoresha benshi, kugabanya ibiciro nubukererwe.

Prefix caking isangira cache kumurongo muremure wa sisitemu kubakoresha benshi, kugabanya ibiciro nubukererwe Amakipe akunze kubona ibisubizo byiza mugihe asobanura ibipimo byiza byimbere imbere, agakomeza inzira yo kuzamura abantu kubibazo byimbere, kandi akurikirana inyungu zibyara umusaruro nibiciro byamakosa mugihe runaka.

KV Cache mubikorwa

vLLM's PagedIcyifuzo cyo gucunga KV cache mubice kugirango ukore ibyifuzo byinshi bihurira kuri GPU imwe neza.

vLLM's PagedIcyifuzo cyo gucunga KV cache mubice kugirango ikore ibyifuzo byinshi bihurijwe hamwe kuri GPU imwe neza Amakipe ubusanzwe abona ibisubizo byiza iyo asobanuye ibipimo byujuje ubuziranenge imbere, agakomeza inzira yo kuzamura abantu kubibazo, kandi akurikirana inyungu zibyara umusaruro nibiciro byamakosa mugihe runaka.

KV Cache mubikorwa

Kugabanya ubwihisho bwa KV kugirango ugabanye neza kugirango uhuze umwanya muremure mububiko buke bwa GPU.

Kugabanya ubwihisho bwa KV kugirango ugabanye neza kugirango uhuze ibice birebire mububiko buke bwa GPU Amakipe ubusanzwe abona ibisubizo byiza iyo asobanuye ibipimo ngenderwaho byimbere imbere, agakomeza inzira yo kuzamura abantu kubibazo, kandi akurikirana inyungu zibyara umusaruro hamwe nibiciro byamakosa mugihe runaka.

Ingaruka & Kurinda

!

Ibintu bifatika bishobora kwinjiza bucece raporo, gushyigikira imigendekere, cyangwa ibisubizo byubushakashatsi.

!

Kwihuta byihuse birashobora gukora ibisubizo bidahuye mubisabwa bisa.

!

Ibyanditswe byumvikana birashobora kugaragara niba kugenzura kugenzura ari ntege.

Igishushanyo mbonera

1

Sobanura imiterere isohoka, amajwi, hamwe nubuziranenge mbere yo gutangira.

Sobanura imiterere isohoka, amajwi, hamwe nubuziranenge mbere yo gutangira. Fata buri ntambwe nk irembo ryibimenyetso: niba ibipimo bitujujwe, hagarika kuzenguruka, funga icyuho, hanyuma noneho wagure imikoreshereze.

2

Ibisubizo byibanze hamwe nisoko yizewe igihe cyose ukuri kwingirakamaro.

Ibisubizo byibanze hamwe nisoko yizewe igihe cyose ukuri kwingirakamaro. Fata buri ntambwe nk irembo ryibimenyetso: niba ibipimo bitujujwe, hagarika kuzenguruka, funga icyuho, hanyuma noneho wagure imikoreshereze.

3

Komeza kugenzura abantu kugenzura ibisubizo byinshi.

Komeza kugenzura abantu kugenzura ibisubizo byinshi. Fata buri ntambwe nk irembo ryibimenyetso: niba ibipimo bitujujwe, hagarika kuzenguruka, funga icyuho, hanyuma noneho wagure imikoreshereze.

4

Kurikirana uburyo bwo kunanirwa no kongera imyitozo cyangwa akazi gahoraho.

Kurikirana uburyo bwo kunanirwa no kongera imyitozo cyangwa akazi gahoraho. Fata buri ntambwe nk irembo ryibimenyetso: niba ibipimo bitujujwe, hagarika kuzenguruka, funga icyuho, hanyuma noneho wagure imikoreshereze.

Komeza Ubushakashatsi