Incamake
Multi-Ikibazo Cyitonderwa (MQA) nigitekerezo cyo kuzigama kwibuka kugoreka ibitekerezo byahinduwe bihuza urufunguzo rumwe nindangagaciro mumutwe wose. Byihuta cyane kubyara inyandiko mugabanya kwibuka moderi igomba guhindagurika.
Ibibazo byinshi-Icyitonderwa ni igice cyururimi-AI ikoreshwa mu gusoma, kubyara, gushyira mu byiciro, no guhindura inyandiko n'imvugo ku gipimo.
Kwibira cyane
Ibisanzwe-imitwe yitabwaho iha buri mutwe ikibazo cyacyo, urufunguzo, nagaciro kateganijwe. Mugihe cyibisekuru, urufunguzo nindangagaciro kubimenyetso byose byashize bigomba kubikwa no gusubirwamo kuri buri ntambwe - iyi KV cache ihinduka icyuho nyamukuru, kubera ko kuyisoma bivuye mumutwe bitinda kuruta imibare ubwayo. Ibibazo byinshi-byitonderwa, byasabwe na Noam Shazeer muri 2019, bigumya kubaza ibibazo bitandukanye kumutwe ariko bigasenya urufunguzo nagaciro kumutwe umwe usangiwe. Ibi bigabanya cache cache kubintu bingana numubare wumutwe, rimwe na rimwe 8x kugeza 64x nto. Igisubizo kirihuta cyane autoregressive decoding hamwe nibirenge byibuke byibirenge, hamwe nibyiza byoroheje. Hagati yo hagati, Itsinda-Ikibazo Cyitonderwa, iringaniza ubucuruzi-buke.
Ubushishozi
Muri MQA, uburemere bwibibazo buracyatanga H gutandukanya ibibazo bitandukanye, ariko urufunguzo rumwe rukumbi hamwe nigiciro kimwe cyagereranijwe mumitwe yose. Buri mutwe ubara ibitekerezo ukoresheje ikibazo cyarwo urufunguzo rumwe nagaciro. Kuberako kashe ya K na V itagipimwa numubare wumutwe, umurongo wibuke mugihe cya decoding ugabanuka cyane - kandi numuyoboro mugari, ntabwo ubara, nibyo byerekana amarembo yihuta kumuvuduko wihuse.
Kumenya byinshi-Kubaza
Multi-Ikibazo Cyitonderwa (MQA) nigitekerezo cyo kuzigama kwibuka kugoreka ibitekerezo byahinduwe bihuza urufunguzo rumwe nindangagaciro mumutwe wose. Byihuta cyane kubyara inyandiko mugabanya kwibuka moderi igomba guhindagurika. Ibibazo byinshi-Icyitonderwa ni igice cyururimi-AI ikoreshwa mu gusoma, kubyara, gushyira mu byiciro, no guhindura inyandiko n'imvugo ku gipimo. Kugirango wubake byimbitse, fata Multi-Query Attention 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 Multi-Query Attention 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.
Gushyira mu bikorwa Isi
Kwihutisha token-by-token generation mubafasha kuganira aho KV cache, ntabwo ari compte mbisi, imipaka yinjira.
__AIU_PROTECTED_11 __ 'PaLM, yakoresheje Multi-Ikibazo Cyitonderwa kugirango ishobore gukora imyanzuro nini nini.
Gukorera abakoresha benshi bahurira kuri GPU imwe mugabanye kubisabwa KV cache yibuka.
Itsinda-Ikibazo Cyitonderwa muri Llama 2 70B na Llama 3, urubyaro rutaziguye ruringaniza umuvuduko wa MQA hamwe nubwiza bwuzuye.
Uburyo bwo Gushyira mu bikorwa
Ibibazo byinshi Byitonderwa mubikorwa
Kwihutisha token-by-token generation mubafasha kuganira aho KV cache, ntabwo ari compte mbisi, imipaka yinjira.
Kwihutisha ibisekuruza-by-ibisekuruza mu bafasha mu biganiro aho cache cache, itari compte mbisi, igabanya ibicuruzwa byinjira Amakipe ubusanzwe abona ibisubizo byiza iyo asobanuye ibipimo byujuje ubuziranenge imbere, agakomeza inzira yo kuzamura abantu kubibazo, kandi akurikirana inyungu zibyara umusaruro hamwe nibiciro byamakosa mugihe runaka.
Ibibazo byinshi Byitonderwa mubikorwa
__AIU_PROTECTED_11 __ 'PaLM, yakoresheje Multi-Ikibazo Cyitonderwa kugirango ishobore gukora imyanzuro nini nini.
__AIU_PROTECTED_11 __ 'PaLM, yakoresheje Multi-Query Attention kugirango ishoboze gukora ibipimo binini binini byerekana amakipe asanzwe abona ibisubizo byiza iyo asobanuye ibipimo byujuje ubuziranenge imbere, agakomeza inzira yo kuzamura abantu kubibazo byimbitse, kandi akurikirana inyungu zibyara umusaruro hamwe nibiciro byamakosa mugihe runaka.
Ibibazo byinshi Byitonderwa mubikorwa
Gukorera abakoresha benshi bahurira kuri GPU imwe mugabanye kubisabwa KV cache yibuka.
Gukorera abakoresha benshi bahurira kuri GPU imwe mugabanye icyifuzo cya KV cache yibuka Amakipe ubusanzwe abona ibisubizo byiza mugihe asobanura ibipimo ngenderwaho byimbere, agakomeza inzira yo kuzamura abantu kubibazo byimbere, kandi akurikirana inyungu zibyara umusaruro nibiciro byamakosa mugihe.
Ibibazo byinshi Byitonderwa mubikorwa
Itsinda-Ikibazo Cyitonderwa muri Llama 2 70B na Llama 3, urubyaro rutaziguye ruringaniza umuvuduko wa MQA hamwe nubwiza bwuzuye.
Itsinda-Ikibazo Cyitonderwa muri Llama 2 70B na Llama 3, urubyaro rutaziguye ruringaniza umuvuduko wa MQA hamwe nubwitonzi bwuzuye bwamakipe ubusanzwe abona ibisubizo byiza iyo asobanuye ibipimo ngenderwaho byimbere, agakomeza inzira yo kuzamura abantu kubibazo byimbere, kandi akurikirana inyungu zibyara umusaruro nibiciro byamakosa mugihe.
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
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.
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.
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.
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.