[{"data":1,"prerenderedAt":1144},["ShallowReactive",2],{"blog-post-nl-\u002Fblog\u002Fpaiton-fp8-beats-nvidias-h200-on-amds-mi300x":3,"blog-posts-sidebar-nl":588},{"id":4,"title":5,"body":6,"categories":561,"date":575,"description":576,"extension":577,"heading":578,"image":579,"meta":580,"navigation":581,"originalUrl":582,"path":583,"seo":584,"slug":585,"socialImage":578,"stem":586,"updated":578,"video":578,"__hash__":587},"blogNl\u002Fblog\u002Fpaiton-fp8-beats-nvidias-h200-on-amds-mi300x.md","Paiton FP8 verslaat NVIDIA's H200 op AMD's MI300X",{"type":7,"value":8,"toc":553},"minimark",[9,13,16,19,27,30,33,74,80,83,86,92,95,98,469,475,482,489,495,534,537,540,543,546],[10,11,12],"p",{},"AI evolueert razendsnel en efficiënte inferentie is essentieel om krachtige modellen in praktijksituaties in te zetten. Bij Eliovp verleggen we voortdurend de grenzen van AI-prestaties. In eerdere artikelen toonden we al aanzienlijke inferentieversnellingen met FP16 en BF16. Nu zetten we opnieuw een grote stap: Paiton behaalt met FP8 sterkere inferentieprestaties op AMD MI300X-GPU's dan NVIDIA's H200. Zowel AMD als NVIDIA ondersteunt FP8, maar onze zorgvuldig geoptimaliseerde kernels maken hier het verschil.",[10,14,15],{},"Het verhaal rond AI-hardware werd lang door één speler gedomineerd. AMD's MI300-serie verandert dat met bijzonder veel rekenkracht. De uitdaging blijft om die capaciteit volledig te benutten. Daar komt Paiton in beeld.",[10,17,18],{},"Onze kernmissie met Paiton is bestaande AI-modellen optimaliseren door de kernels voor inferentie nauwkeurig af te stemmen op AMD-architecturen. We analyseren de onderliggende bewerkingen, herschrijven en fuseren ze en stemmen ze af op de specifieke sterke punten van AMD-hardware. Het resultaat is een aanzienlijk hogere inferentiesnelheid en een efficiënter gebruik van resources.",[20,21,23],"h3",{"id":22},"testopstelling-en-methodologie",[24,25,26],"strong",{},"Testopstelling en methodologie",[10,28,29],{},"Voor transparante en reproduceerbare resultaten documenteren we onze benchmarkopstelling:",[10,31,32],{},"Zoals altijd kozen we voor de best mogelijke configuratie om de vergelijking eerlijk te houden.",[34,35,36,50,56,62,68],"ul",{},[37,38,39,42,43],"li",{},[24,40,41],{},"Inferentiebibliotheek:"," vLLM v0.9.0 + ",[44,45,49],"a",{"href":46,"rel":47},"https:\u002F\u002Fhuggingface.co\u002Famd\u002FLlama-3.1-70B-Instruct-FP8-KV",[48],"nofollow","amd\u002FLlama-3.1-70B-Instruct-FP8-KV",[37,51,52,55],{},[24,53,54],{},"Hardware:"," AMD MI300X (192GB HBM3) versus NVIDIA H200 (141GB HBM3e)",[37,57,58,61],{},[24,59,60],{},"Softwarestack:"," ROCm 6.3.1 op Ubuntu 22.04 (een upgrade naar 6.4 kan nog betere resultaten opleveren); CUDA 12.x op Ubuntu 22.04",[37,63,64,67],{},[24,65,66],{},"Metingen:"," Gemiddelden over 10 inferentieruns, met zowel cold-start- als steady-state-Time to First Token (TTFT) en end-to-end-latency (van API-oproep tot laatste token)",[37,69,70,73],{},[24,71,72],{},"Batchgroottes:"," 1 tot 128, voor zowel interactieve AI-workloads (1 tot 64) als het uiterste voor batchverwerking (128)",[20,75,77],{"id":76},"het-voordeel-van-fp8-het-tijdperk-van-efficiëntie",[24,78,79],{},"Het voordeel van FP8: het tijdperk van efficiëntie",[10,81,82],{},"De introductie van FP8-precisie (8-bit floating point) was een belangrijke stap naar efficiëntere AI-inferentie. FP8 verkleint de geheugenvoetafdruk en verlaagt de rekenintensiteit. Daardoor kunnen grotere modellen worden ingezet of kunnen bestaande modellen met een veel hogere throughput draaien terwijl ze minder geheugen gebruiken. Moderne AI-hardware van zowel AMD als NVIDIA ondersteunt FP8, maar om het volledige potentieel te benutten is sterk geoptimaliseerde software nodig.",[10,84,85],{},"We hebben intensief gewerkt aan de integratie en optimalisatie van onze FP8-kernels voor AMD. Onze recente benchmarks laten een duidelijke overwinning zien voor de AMD MI300X met Paiton's geoptimaliseerde kernels.",[20,87,89],{"id":88},"paiton-op-amd-mi300x-een-nieuwe-standaard-zetten",[24,90,91],{},"Paiton op AMD MI300X: een nieuwe standaard zetten",[10,93,94],{},"Uit onze interne tests blijkt dat de AMD MI300X-GPU met Paiton's geoptimaliseerde kernels aantoonbaar betere resultaten behaalt dan de NVIDIA H200-GPU bij FP8-inferentie met het amd\u002FLlama-3.1-70B-Instruct-FP8-KV-model.",[10,96,97],{},"Hier zijn de benchmarkresultaten waarin de prestaties van NVIDIA H200 en AMD MI300X worden vergeleken met de geoptimaliseerde kernels van Paiton:",[99,100,101,138],"table",{},[102,103,104],"thead",{},[105,106,107,111,114,117,120,123,126,129,132,135],"tr",{},[108,109,110],"th",{},"Batch",[108,112,113],{},"H200 (req\u002Fs)",[108,115,116],{},"MI300X + Paiton (req\u002Fs)",[108,118,119],{},"H200 (tok\u002Fs)",[108,121,122],{},"MI300X + Paiton (tok\u002Fs)",[108,124,125],{},"H200 E2E (ms)",[108,127,128],{},"MI300X E2E (ms)",[108,130,131],{},"H200 TTFT (ms)",[108,133,134],{},"MI300X TTFT (ms)",[108,136,137],{},"Winnaar",[139,140,141,184,225,266,307,348,389,429],"tbody",{},[105,142,143,147,150,155,158,163,166,171,176,179],{},[144,145,146],"td",{},"1",[144,148,149],{},"0,16",[144,151,152],{},[24,153,154],{},"0,17",[144,156,157],{},"39,9",[144,159,160],{},[24,161,162],{},"43,4",[144,164,165],{},"640,7",[144,167,168],{},[24,169,170],{},"589,5",[144,172,173],{},[24,174,175],{},"136,3",[144,177,178],{},"138,6",[144,180,181],{},[24,182,183],{},"Paiton",[105,185,186,189,192,197,200,205,208,213,216,221],{},[144,187,188],{},"2",[144,190,191],{},"0,31",[144,193,194],{},[24,195,196],{},"0,34",[144,198,199],{},"78,5",[144,201,202],{},[24,203,204],{},"87,0",[144,206,207],{},"518,5",[144,209,210],{},[24,211,212],{},"477,7",[144,214,215],{},"133,6",[144,217,218],{},[24,219,220],{},"122,4",[144,222,223],{},[24,224,183],{},[105,226,227,230,233,238,241,246,249,254,257,262],{},[144,228,229],{},"4",[144,231,232],{},"0,60",[144,234,235],{},[24,236,237],{},"0,67",[144,239,240],{},"129,6",[144,242,243],{},[24,244,245],{},"172,0",[144,247,248],{},"562,2",[144,250,251],{},[24,252,253],{},"441,6",[144,255,256],{},"134,3",[144,258,259],{},[24,260,261],{},"132,6",[144,263,264],{},[24,265,183],{},[105,267,268,271,274,279,282,287,290,295,300,303],{},[144,269,270],{},"8",[144,272,273],{},"1,18",[144,275,276],{},[24,277,278],{},"1,31",[144,280,281],{},"225,0",[144,283,284],{},[24,285,286],{},"252,1",[144,288,289],{},"587,6",[144,291,292],{},[24,293,294],{},"493,3",[144,296,297],{},[24,298,299],{},"269,9",[144,301,302],{},"280,9",[144,304,305],{},[24,306,183],{},[105,308,309,312,315,320,323,328,331,336,341,344],{},[144,310,311],{},"16",[144,313,314],{},"2.21",[144,316,317],{},[24,318,319],{},"2,45",[144,321,322],{},"343,1",[144,324,325],{},[24,326,327],{},"470,1",[144,329,330],{},"560,6",[144,332,333],{},[24,334,335],{},"502,5",[144,337,338],{},[24,339,340],{},"461,3",[144,342,343],{},"513,8",[144,345,346],{},[24,347,183],{},[105,349,350,353,356,361,364,369,372,377,380,385],{},[144,351,352],{},"32",[144,354,355],{},"3,93",[144,357,358],{},[24,359,360],{},"4,07",[144,362,363],{},"591,8",[144,365,366],{},[24,367,368],{},"814,5",[144,370,371],{},"659,1",[144,373,374],{},[24,375,376],{},"640,6",[144,378,379],{},"1188,7",[144,381,382],{},[24,383,384],{},"1187,5",[144,386,387],{},[24,388,183],{},[105,390,391,394,399,402,407,410,415,418,421,426],{},[144,392,393],{},"64",[144,395,396],{},[24,397,398],{},"6,64",[144,400,401],{},"6,24",[144,403,404],{},[24,405,406],{},"1297,4",[144,408,409],{},"1179,7",[144,411,412],{},[24,413,414],{},"789,3",[144,416,417],{},"812,2",[144,419,420],{},"2362,3",[144,422,423],{},[24,424,425],{},"1880,3",[144,427,428],{},"Gelijkspel",[105,430,431,434,439,442,447,450,455,458,461,466],{},[144,432,433],{},"128",[144,435,436],{},[24,437,438],{},"9,75",[144,440,441],{},"9.01",[144,443,444],{},[24,445,446],{},"1821,9",[144,448,449],{},"1655,8",[144,451,452],{},[24,453,454],{},"607,7",[144,456,457],{},"635,5",[144,459,460],{},"3633,3",[144,462,463],{},[24,464,465],{},"3502.0",[144,467,468],{},"H200",[10,470,471,474],{},[24,472,473],{},"Opmerking:"," In voorlopige tests presteerden Paiton's FP8-kernels ook beter dan AMD's eigen Aiter-engine op MI300X.",[10,476,477],{},[478,479],"img",{"alt":480,"src":481},"","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Fh200vsmi300xfp8.webp",[10,483,484,485,488],{},"De resultaten zijn duidelijk: ",[24,486,487],{},"met Paiton verwerkt de AMD MI300X Llama-3.1-70B-Instruct-FP8-KV-verzoeken bij kleine tot middelgrote batchgroottes met een hogere throughput en lagere latency dan de NVIDIA H200. Ook de Time to First Token (TTFT) is vaak beter."," Dat toont rechtstreeks de kracht van gerichte kerneloptimalisatie. De NVIDIA H200 blijft sterk bij de hoogste batchgroottes, maar Paiton heeft een duidelijk voordeel in courante praktijkscenario's met kleinere, frequentere verzoeken, zoals bij interactieve AI-applicaties. Voor eindgebruikers betekent dat snellere antwoorden en een efficiënter gebruik van AMD-hardware.",[20,490,492],{"id":491},"waarom-dit-voor-u-belangrijk-is",[24,493,494],{},"Waarom dit voor u belangrijk is",[34,496,497,503,514,524],{},[37,498,499,502],{},[24,500,501],{},"Benut het volledige potentieel van AMD:"," Wie in geavanceerde hardware zoals AMD MI300X-GPU's investeert, wil die capaciteit volledig benutten en geen prestaties verliezen door generieke software. Paiton haalt zoveel mogelijk uit elke rekencyclus. Onze nauwkeurig afgestemde kernels beperken inactieve tijd en maximaliseren de nuttige rekenkracht voor AI-inferentieworkloads.",[37,504,505,508,509,513],{},[24,506,507],{},"Kosteneffectieve AI-implementatie:"," Hogere inferentie-efficiëntie vertaalt zich direct in tastbare kostenbesparingen. Wanneer uw modellen sneller en efficiënter werken, kunt u meer aanvragen verwerken of bestaande workloads in minder tijd voltooien. Dit heeft een directe invloed op uw operationele kosten, of u nu een lokaal datacenter beheert of gebruikmaakt van cloudgebaseerde GPU-instances. Na verloop van tijd kunnen deze optimalisaties leiden tot ",[510,511,512],"em",{},"substantiële verlagingen van uw totale eigendomskosten"," voor de AI-infrastructuur.",[37,515,516,519,520,523],{},[24,517,518],{},"Maak uw deployments toekomstbestendig:"," AI-modellen evolueren voortdurend naar grotere, complexere architecturen en precisieformaten zoals FP8. Naarmate hun rekenbehoeften groeien, worden sterk geoptimaliseerde inferentieoplossingen essentieel om prestaties en schaalbaarheid te behouden. ",[510,521,522],{},"De voortdurende ontwikkeling van Paiton"," helpt uw AI-deployments klaar te maken voor de volgende generatie modellen en precisievereisten.",[37,525,526,529,530,533],{},[24,527,528],{},"Bredere hardwarekeuze:"," Ons werk met Paiton stelt ontwikkelaars en organisaties in staat om met vertrouwen AMD te kiezen voor hun veeleisende behoeften op het gebied van AI-inferentie. Door ",[510,531,532],{},"superieure prestaties te demonstreren op AMD MI210, MI250X, MI300X, MI325X",", MI355X, bevorderen we een competitiever en innovatiever hardware-ecosysteem, waardoor u meer flexibiliteit en opties krijgt bij het ontwerpen van uw AI-infrastructuur. Deze concurrentie stimuleert innovatie in de hele sector, waar uiteindelijk alle gebruikers van profiteren.",[10,535,536],{},"Het tijdperk van uniforme AI-optimalisatie loopt snel ten einde. Paiton loopt voorop met gespecialiseerde, krachtige oplossingen die zorgvuldig voor AMD-GPU's zijn ontworpen. Met onze nieuwste verbeteringen, waaronder de FP8-optimalisaties, optimaliseren we niet alleen bestaande prestaties, we verleggen de grens van wat mogelijk is voor AI-inferentie op AMD-hardware.",[10,538,539],{},"Blijf op de hoogte voor meer diepgaande technische uitsplitsingen en verdere benchmarkreleases terwijl we de grenzen van AI-prestaties blijven verleggen. Tijdens deze FP8-benchmarks hebben we aanvullende optimalisatietechnieken ontdekt die we zullen laten zien in komende diepgaande posts! We zullen binnenkort opwindende resultaten delen over Tensor Parallelism (TP), waarbij Paiton superieure prestaties en schaalbaarheid blijft demonstreren en zelfs AMD's eigen AITER-engine overtreft in onze interne tests. Als u AI-modellen op AMD-hardware gebruikt, is het tijd om het Paiton-verschil te ervaren en te zien hoe onze kerneloptimalisaties uw mogelijkheden voor AI-inferentie kunnen verbeteren.",[10,541,542],{},"Als u AI-modellen op AMD-hardware gebruikt, is het tijd om het Paiton-verschil te ervaren en te zien hoe onze kerneloptimalisaties uw mogelijkheden voor AI-inferentie kunnen verbeteren.",[10,544,545],{},"Neem contact op voor een demo en verbeter uw AI-inferentieprestaties.",[10,547,548],{},[510,549,550],{},[24,551,552],{},"Het Paiton-team",{"title":480,"searchDepth":554,"depth":554,"links":555},2,[556,558,559,560],{"id":22,"depth":557,"text":26},3,{"id":76,"depth":557,"text":79},{"id":88,"depth":557,"text":91},{"id":491,"depth":557,"text":494},[562,563,183,564,565,566,567,568,569,570,571,572,573,574],"Alle","Kunstmatige intelligentie","Niet gecategoriseerd","AMD MI300X","Koude startoptimalisatie","Bedrijfs-AI","Generatieve AI","GPU-prestaties","Inferentielatentie","Grote taalmodellen","Llama 3.1 405B","Model serving","vLLM-optimalisatie","2025-06-08T19:12:40","Vergelijk Paiton op AMD MI300X met NVIDIA H200 voor Llama 3.1 70B FP8: throughput, wachttijd tot het eerste token en latency bij diverse batchgroottes.","md",null,"\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Fblognewfp8.webp",{},true,"https:\u002F\u002Feliovp.com\u002Fpaiton-fp8-beats-nvidias-h200-on-amds-mi300x\u002F","\u002Fblog\u002Fpaiton-fp8-beats-nvidias-h200-on-amds-mi300x",{"title":5,"description":576},"paiton-fp8-beats-nvidias-h200-on-amds-mi300x","blog\u002Fpaiton-fp8-beats-nvidias-h200-on-amds-mi300x","XEsoQMJ7foax8MZHGosAAJzf-330XQhDGkR4osRjQ5c",[589,601,614,624,633,648,657,666,675,685,696,706,718,728,738,747,758,788,799,821,839,857,876,893,909,920,936,951,962,971,979,993,995,1006,1017,1027,1040,1050,1063,1074,1084,1095,1104,1116,1126,1135],{"path":590,"title":591,"description":592,"date":593,"slug":594,"image":595,"originalUrl":596,"categories":597},"\u002Fblog\u002Fpaiton-idol-radeon-ai-pro-r9700","De Radeon AI PRO R9700 doet ook 3D: Idol in 16,4 seconden","Idol maakt een 3D Gaussian splat in 16,44 seconden op één Radeon AI PRO R9700 met Paiton, tegenover 39,22 seconden voor standaard-Idol op dezelfde GPU.","2026-11-06T09:00:00Z","paiton-idol-radeon-ai-pro-r9700","\u002Fasset\u002Fimages\u002Fblog\u002Fpaiton-idol\u002Fhero-nl.webp","https:\u002F\u002Feliovp.com\u002Fblog\u002Fpaiton-idol-radeon-ai-pro-r9700",[183,598,599,600],"AMD Radeon","Lokale AI","3D-generatie",{"path":602,"title":603,"description":604,"date":605,"slug":606,"image":607,"originalUrl":608,"categories":609},"\u002Fblog\u002Fpaiton-deepseek-v41-flash-amd-instinct-mi350p","Deepseek V4.1 Flash op één MI350P","DeepSeek V4.1 Flash op één MI350P met 144 GB: 77,9 tokens\u002Fs bij één verzoek en 1.107,6 in een batch van 512, met Paiton en expertberekeningen op CPU.","2026-11-03T12:00:00Z","paiton-deepseek-v41-flash-amd-instinct-mi350p","\u002Fasset\u002Fimages\u002Fblog\u002Fpaiton-deepseek-v41\u002Fhero-nl.webp","https:\u002F\u002Feliovp.com\u002Fblog\u002Fpaiton-deepseek-v41-flash-amd-instinct-mi350p",[183,610,611,612,613],"AMD Instinct","AI-inferentie","DeepSeek","Kwantisatie",{"path":615,"title":616,"description":617,"date":618,"slug":619,"image":620,"originalUrl":621,"categories":622},"\u002Fblog\u002Fpaiton-qwen38-flash-next-amd-instinct-mi350p","Qwen3.8 Flash Next op MI350P: dubbel zo snel | Paiton","Qwen3.8 Flash Next op één AMD MI350P: 2,24× de decodesnelheid van de geteste vLLM-configuratie bij één verzoek en circa 2,2 miljoen gedeelde KV-cachetokens.","2026-10-30T12:00:00Z","paiton-qwen38-flash-next-amd-instinct-mi350p","\u002Fasset\u002Fimages\u002Fblog\u002Fpaiton-mi350p\u002Fhero-nl.webp","https:\u002F\u002Feliovp.com\u002Fblog\u002Fpaiton-qwen38-flash-next-amd-instinct-mi350p",[183,610,611,623,613],"Qwen",{"path":625,"title":626,"description":627,"date":628,"slug":629,"image":630,"originalUrl":631,"categories":632},"\u002Fblog\u002Fpaiton-qwen38-3bit-accuracy-prefix-caching-mtp","Qwen3.8 Flash Next: 3-bit dicht bij 16-bit nauwkeurigheid, met MTP-prefixcaching","Paitons nieuwe 3-bit Qwen3.8-gewichten benaderen 16-bit taakscores op twee R9700-kaarten. Native MTP-prefixcaching hervat een prompt van 200K in 0,68 seconde. Resultaten, grenzen en installatie.","2026-10-24T18:45:00Z","paiton-qwen38-3bit-accuracy-prefix-caching-mtp","\u002Fasset\u002Fimages\u002Fblog\u002Fpaiton-qwen38-3bit-mtp\u002Fhero-nl.webp","https:\u002F\u002Feliovp.com\u002Fblog\u002Fpaiton-qwen38-3bit-accuracy-prefix-caching-mtp",[183,598,599,623,613],{"path":634,"title":635,"description":636,"date":637,"slug":638,"image":639,"originalUrl":640,"categories":641},"\u002Fblog\u002Fnvidia-dsx-pod-vera-rubin-modular-data-centers","Nvidia confirms the modular DC direction","NVIDIA DSX POD brengt Vera Rubin AI-fabrieken naar modulaire datacenters. ElioVP bespreekt terreinvoorbereiding, koeling en de aanpak achter ModFlex.","2026-10-21T13:00:00Z","nvidia-dsx-pod-vera-rubin-modular-data-centers","\u002Fasset\u002Fimages\u002Fblog\u002Fnvidia-dsx-pod-modflex\u002Fhero.webp","https:\u002F\u002Feliovp.com\u002Fblog\u002Fnvidia-dsx-pod-vera-rubin-modular-data-centers",[642,643,644,645,646,647],"Modular DC","AI-infrastructuur","ModFlex","NVIDIA","Vera Rubin","Vloeistofkoeling",{"path":649,"title":650,"description":651,"date":652,"slug":653,"image":654,"originalUrl":655,"categories":656},"\u002Fblog\u002Fpaiton-qwen38-flash-next-4bit-radeon-ai-pro-r9700","Qwen3.8 Flash Next in 4-bit op 2 × Radeon R9700: getest tegenover 16-bit","Paiton draait Qwen3.8 Flash Next in 4-bit op twee R9700-kaarten: 96,8% GSM8K, 96,3% HumanEval, 189,8 tokens\u002Fs en een optionele RAM-prefixcache. Kwaliteit, snelheid en installatie.","2026-10-12T15:00:00Z","paiton-qwen38-flash-next-4bit-radeon-ai-pro-r9700","\u002Fasset\u002Fimages\u002Fblog\u002Fpaiton-qwen38-flash-next-4bit\u002Fhero-nl.webp","https:\u002F\u002Feliovp.com\u002Fblog\u002Fpaiton-qwen38-flash-next-4bit-radeon-ai-pro-r9700",[183,598,599,623,613],{"path":658,"title":659,"description":660,"date":661,"slug":662,"image":663,"originalUrl":664,"categories":665},"\u002Fblog\u002Fpaiton-qwen38-flash-next-radeon-ai-pro-r9700","Qwen3.8 Flash Next op 2 × Radeon AI PRO R9700: 216 tokens\u002Fs, 200K-context","Paiton draait Qwen3.8 Flash Next met 3-bit experts op twee R9700-kaarten: 216,3 tokens\u002Fs, 565,1 tokens\u002Fs samen en een aparte 200K-modus. Metingen, kwaliteit en installatie.","2026-10-10T10:30:00Z","paiton-qwen38-flash-next-radeon-ai-pro-r9700","\u002Fasset\u002Fimages\u002Fblog\u002Fpaiton-qwen38-flash-next\u002Fhero-nl.webp","https:\u002F\u002Feliovp.com\u002Fblog\u002Fpaiton-qwen38-flash-next-radeon-ai-pro-r9700",[183,598,599,623,613],{"path":667,"title":668,"description":669,"date":670,"slug":671,"image":672,"originalUrl":673,"categories":674},"\u002Fblog\u002Fpaiton-qwen38-w3a4-radeon-ai-pro-r9700","Qwen3.8 27B op 1 × Radeon AI PRO R9700: 3-bit gewichten, 20% snellere decode","Qwen3.8 27B op één R9700: 19,9% snellere gewogen decode, een nieuwe 4-bit cache, 200K-context en optionele beeldinvoer. Metingen en Paiton-installatie.","2026-09-27T09:00:00Z","paiton-qwen38-w3a4-radeon-ai-pro-r9700","\u002Fasset\u002Fimages\u002Fblog\u002Fpaiton-qwen38-w3a4\u002Fhero-nl.webp","https:\u002F\u002Feliovp.com\u002Fblog\u002Fpaiton-qwen38-w3a4-radeon-ai-pro-r9700",[183,598,599,623,613],{"path":676,"title":677,"description":678,"date":679,"slug":680,"image":681,"originalUrl":682,"categories":683},"\u002Fblog\u002Fpaiton-qwen-image-21-radeon-ai-pro-r9700","Qwen-Image 2.1 op 1 × Radeon AI PRO R9700: 2048×2048-beelden in 103 seconden","Genereer lokaal Qwen-Image 2.1-beelden van 2048×2048 pixels met 1 × Radeon AI PRO R9700. De Paiton v1.0.2-container mat 103,29 seconden per opgewarmd verzoek, inclusief de PNG-respons.","2026-09-23T09:00:00Z","paiton-qwen-image-21-radeon-ai-pro-r9700","\u002Fasset\u002Fimages\u002Fblog\u002Fpaiton-qwen-image-21\u002Fhero-nl.webp","https:\u002F\u002Feliovp.com\u002Fblog\u002Fpaiton-qwen-image-21-radeon-ai-pro-r9700",[183,598,599,684,623],"Beeldgeneratie",{"path":686,"title":687,"description":688,"date":689,"slug":690,"image":691,"originalUrl":692,"categories":693},"\u002Fblog\u002Fpaiton-qwen38-mxfp4-dflash2-r9700","Qwen3.8: 400,7 tok\u002Fs op één R9700 | Paiton","Qwen3.8 op één R9700: 400,7 tok\u002Fs met ROCm 10 en vLLM 0.29, plus publieke 200K\u002F220K-chatprofielen. Benchmarks, beperkingen en startopdrachten.","2026-09-16T07:30:00Z","paiton-qwen38-mxfp4-dflash2-r9700","\u002Fasset\u002Fimages\u002Fblog\u002Fpaiton-qwen38-mxfp4\u002Fupdate-2026-09-19\u002Fhero.webp","https:\u002F\u002Feliovp.com\u002Fblog\u002Fpaiton-qwen38-mxfp4-dflash2-r9700",[183,598,599,611,694,571,695],"Inferentie-optimalisatie","vLLM",{"path":697,"title":698,"description":699,"date":700,"slug":701,"image":702,"originalUrl":703,"categories":704},"\u002Fblog\u002Fpaiton-qwen38-neo-gguf-vllm-r9700","Qwen3.8 GGUF in vLLM: sneller antwoord op één Radeon","Draai de originele NEO CODER MAX GGUF met Paiton in vLLM op een R9700. Bekijk de gemeten responstijden, beeldinvoer en lokale installatie.","2026-09-14T07:30:00Z","paiton-qwen38-neo-gguf-vllm-r9700","\u002Fasset\u002Fimages\u002Fblog\u002Fpaiton-neo-gguf\u002F00-hero-neo-gguf-r9700.webp","https:\u002F\u002Feliovp.com\u002Fblog\u002Fpaiton-qwen38-neo-gguf-vllm-r9700",[183,598,599,705,695],"GGUF",{"path":707,"title":708,"description":709,"date":710,"slug":711,"image":712,"originalUrl":713,"categories":714},"\u002Fblog\u002Fpaiton-minimax-h3-radeon-ai-pro-r9700","MiniMax H3 op Radeon: 15 seconden video met stereogeluid","Paiton genereert lokaal 15 seconden MiniMax H3-video met stereogeluid op één Radeon AI PRO R9700 in 5 min 33 s, met 16,7% minder wachttijd dan stock.","2026-09-09T07:30:00Z","paiton-minimax-h3-radeon-ai-pro-r9700","\u002Fasset\u002Fimages\u002Fblog\u002Fpaiton-minimax-h3\u002F00-featured-minimax-h3-r9700.webp","https:\u002F\u002Feliovp.com\u002Fblog\u002Fpaiton-minimax-h3-radeon-ai-pro-r9700",[183,598,599,715,716,717],"Videogeneratie","MiniMax H3","ComfyUI",{"path":719,"title":720,"description":721,"date":722,"slug":723,"image":724,"originalUrl":725,"categories":726},"\u002Fblog\u002Fpaiton-flux2-klein-radeon-ai-pro-r9700","Lokale FLUX.2 klein op Radeon AI PRO R9700: sneller beelden genereren met minder VRAM","Paiton genereert FLUX.2 klein-beelden van 1024 × 1024 in 1,054 seconden op een R9700, met 16,2% minder generatietijd en 33,4% minder piekallocatie in Torch.","2026-09-07T09:00:00","paiton-flux2-klein-radeon-ai-pro-r9700","\u002Fasset\u002Fimages\u002Fblog\u002Fpaiton-flux2-klein\u002Ffox-paiton.webp","https:\u002F\u002Feliovp.com\u002Fblog\u002Fpaiton-flux2-klein-radeon-ai-pro-r9700",[183,598,599,684,727,717],"FLUX",{"path":729,"title":730,"description":731,"date":732,"slug":733,"image":734,"originalUrl":735,"categories":736},"\u002Fblog\u002Fpaiton-ornith15-radeon-ai-pro-r9700","Ornith 1.5 haalt 44,6 tok\u002Fs op één Radeon AI PRO R9700","Paiton draait Ornith 1.5 35B A3B op één Radeon AI PRO R9700 met 44,63 outputtokens per seconde, 27% sneller en met 21,3% lagere gemodelleerde kosten.","2026-09-05T09:00:00","paiton-ornith15-radeon-ai-pro-r9700","\u002Fasset\u002Fimages\u002Fblog\u002Fpaiton-ornith15\u002F00-featured-ornith15-r9700.webp","https:\u002F\u002Feliovp.com\u002Fblog\u002Fpaiton-ornith15-radeon-ai-pro-r9700",[183,563,598,611,569,570,694,571,695,737],"Kostenefficiëntie",{"path":739,"title":740,"description":741,"date":742,"slug":743,"image":744,"originalUrl":745,"categories":746},"\u002Fblog\u002Fpaiton-qwen38-radeon-ai-pro-r9700","Paiton: 21% meer Qwen3.8-doorvoer op Radeon AI PRO R9700","Paiton draait AMD's Qwen3.8 27B op één Radeon AI PRO R9700 met 39,77 outputtokens per seconde. Dat levert 21% meer throughput en 17,4% lagere gemodelleerde kosten op.","2026-09-04T09:00:00","paiton-qwen38-radeon-ai-pro-r9700","\u002Fasset\u002Fimages\u002Fblog\u002Fpaiton-r9700\u002F00-featured-paiton-r9700.webp","https:\u002F\u002Feliovp.com\u002Fblog\u002Fpaiton-qwen38-radeon-ai-pro-r9700",[183,563,598,611,569,570,694,571,695,737],{"path":748,"title":749,"description":750,"date":751,"slug":752,"image":753,"originalUrl":578,"categories":754},"\u002Fblog\u002Fai-data-center-power-requirements-gpu-per-megawatt","Stroomvereisten voor AI-datacenters: de GPU-per-MW-illusie","Waarom verschillen GPU-aantallen per megawatt? Lees hoe PUE, piekbelasting, opslag, netwerken en koeling de inzetbare AI-capaciteit bepalen.","2026-07-27T23:52:00","ai-data-center-power-requirements-gpu-per-megawatt","\u002Fasset\u002Fimages\u002Fblog\u002Fai-data-center-power-requirements-gpu-per-megawatt\u002Fgpu-per-megawatt-illusion.webp",[562,643,755,644,756,757],"Datacenters","HPC","AMD Helios",{"path":759,"title":760,"description":761,"date":762,"slug":763,"image":764,"originalUrl":765,"categories":766},"\u002Fblog\u002Fpaiton-returns-to-its-diffusion-roots-optimizing-wan2-2-t2v-a14b-on-amd-mi355x","Wan2.2-videogeneratie: Paiton op AMD MI355X","Vergelijk Wan2.2-videogeneratie op AMD MI355X met Paiton en NVIDIA B200 via Diffusers. Lees hoe we diffusiemodellen optimaliseren.","2026-06-10T14:04:04","paiton-returns-to-its-diffusion-roots-optimizing-wan2-2-t2v-a14b-on-amd-mi355x","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Fpaitonwan2.webp","https:\u002F\u002Feliovp.com\u002Fpaiton-returns-to-its-diffusion-roots-optimizing-wan2-2-t2v-a14b-on-amd-mi355x\u002F",[562,563,183,767,768,769,770,771,772,773,774,568,775,776,777,778,779,645,780,781,183,782,783,784,785,786,787],"14B","AMD","B200","Benchmarks","Blackwell","Compute","Diffusie","Eliovp","GPU","Hardware","Inferentie","Instinct","MI355x","On-premises","Optimalisatie","Soevereine AI","T2V","Tekst-naar-video","Tuning","Video-generatie","Wan2.2",{"path":789,"title":790,"description":791,"date":792,"slug":793,"image":794,"originalUrl":795,"categories":796},"\u002Fblog\u002Ffrom-the-attic-to-the-front-page-eliovp-recognized-as-a-pioneer-in-chip-optimization-data-center-infrastructure","ElioVP in De Tijd: chipoptimalisatie en datacenters","Lees hoe De Tijd ElioVP belicht, van de oorsprong in chipoptimalisatie tot het werk aan modulaire datacenters en koeling voor hoge vermogensdichtheid.","2026-02-10T20:48:12","from-the-attic-to-the-front-page-eliovp-recognized-as-a-pioneer-in-chip-optimization-data-center-infrastructure","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Fphysicalnewspaper.webp","https:\u002F\u002Feliovp.com\u002Ffrom-the-attic-to-the-front-page-eliovp-recognized-as-a-pioneer-in-chip-optimization-data-center-infrastructure\u002F",[562,563,797,564,768,798,797,645],"Modulaire DC","De Tijd",{"path":800,"title":801,"description":802,"date":803,"slug":804,"image":805,"originalUrl":806,"categories":807},"\u002Fblog\u002Fprivacy-is-geen-it-probleem-meer-het-is-een-strategische-prioriteit","AI en privacy: een strategische prioriteit in de Benelux","Privacyrisico's van generatieve AI, vertrouwen, dataopslag en governance. Waarom bedrijven in de Benelux veilige AI strategisch moeten benaderen.","2026-01-29T13:51:11","privacy-is-geen-it-probleem-meer-het-is-een-strategische-prioriteit","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Fheaderimage.webp","https:\u002F\u002Feliovp.com\u002Fprivacy-is-geen-it-probleem-meer-het-is-een-strategische-prioriteit\u002F",[562,563,808,564,809,810,811,812,813,814,815,816,774,817,568,818,819,820],"Trending","AI Act","Antropomorfisme","AVG","Benelux","ChatGPT","Cyberbeveiliging","Databeheer","Gegevensbeveiliging","GDPR","Microsoft Copilot","Privacy","Shadow AI",{"path":822,"title":823,"description":824,"date":825,"slug":826,"image":827,"originalUrl":828,"categories":829},"\u002Fblog\u002Fitsme-bij-ons-is-het-its-not-me-en-dit-is-waarom","Waarom wij itsme niet gebruiken: privacy en soevereiniteit","Waarom ElioVP itsme niet gebruikt: onze afwegingen rond identiteitsmetadata, cloudafhankelijkheid, privacy en datasoevereiniteit.","2025-11-27T09:32:14","itsme-bij-ons-is-het-its-not-me-en-dit-is-waarom","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Ffrontimage.webp","https:\u002F\u002Feliovp.com\u002Fitsme-bij-ons-is-het-its-not-me-en-dit-is-waarom\u002F",[562,830,831,832,814,833,834,835,817,836,837,838,819],"AWS","Belgian Mobile ID","CLOUD Act","Datasoevereiniteit","Digitale identiteit","eIDAS","itsme","Liberty Global","MyGov.be",{"path":840,"title":841,"description":842,"date":843,"slug":844,"image":845,"originalUrl":846,"categories":847},"\u002Fblog\u002Ffield-report-the-reality-of-building-agentic-ai-in-2025","Praktijkrapport: de realiteit van Agentic AI bouwen in 2025","Praktijklessen over lokale AI-agents in 2025 gaan in op workflowontwerp, observability, modeltraining, hallucinaties en GPU-geheugenlimieten.","2025-11-25T14:03:39","field-report-the-reality-of-building-agentic-ai-in-2025","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Ffieldreport.webp","https:\u002F\u002Feliovp.com\u002Ffield-report-the-reality-of-building-agentic-ai-in-2025\u002F",[562,563,848,808,849,850,851,852,567,853,854,855,782,856],"Oplossingen","Agentic AI","AI-techniek","AI-strategie","Autonome agenten","Lokale LLM","Modelverfijning","AI op locatie","VRAM-optimalisatie",{"path":858,"title":859,"description":860,"date":861,"slug":862,"image":863,"originalUrl":864,"categories":865},"\u002Fblog\u002Fthe-synthetic-unicorn-bubble","De synthetische unicornzeepbel","Een analyse van investeringsrisico’s bij AI-neoclouds: circulaire financiering, infrastructuurclaims, contractvoorwaarden en due diligence.","2025-11-24T19:22:28","the-synthetic-unicorn-bubble","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Fsyntheticunicorn.webp","https:\u002F\u002Feliovp.com\u002Fthe-synthetic-unicorn-bubble\u002F",[562,563,808,866,867,868,869,870,871,872,873,874,875],"AI Infrastructure","AI Neocloud","Circulaire financiering","GPU Cloud","Beleggingsrisico's","Opstartwaardering","Synthetische bubbel","Technische analyse","Vaporware","Durfkapitaal",{"path":877,"title":878,"description":879,"date":880,"slug":881,"image":882,"originalUrl":883,"categories":884},"\u002Fblog\u002Fbuilding-the-engine-for-the-ai-race-the-4-month-path-to-nvidia-gb300-nvl72-power","NVIDIA GB300 NVL72: modulair datacenter in vier maanden","Ontdek een modulair datacenterontwerp voor NVIDIA GB300 NVL72, met redundante voeding, hybride koeling en een bouwplanning van vier maanden.","2025-11-20T14:10:19","building-the-engine-for-the-ai-race-the-4-month-path-to-nvidia-gb300-nvl72-power","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Fsuperpodmodflexfrontimage.webp","https:\u002F\u002Feliovp.com\u002Fbuilding-the-engine-for-the-ai-race-the-4-month-path-to-nvidia-gb300-nvl72-power\u002F",[562,797,564,885,643,886,887,647,888,889,890,891,892],"150 kW-rack","DLC","Hoge dichtheid","Modulair datacenter","NVIDIA Blackwell Ultra","NVIDIA GB300","NVL72","Snelle implementatie",{"path":894,"title":895,"description":896,"date":897,"slug":898,"image":899,"originalUrl":900,"categories":901},"\u002Fblog\u002Fwhy-cuda-translation-wont-unlock-amds-real-potential","CUDA-vertaling versus AMD-gerichte optimalisatie","Waarom CUDA-compatibiliteit niet hetzelfde is als AMD-prestaties: over ROCm, HIP, kerneloptimalisatie en hardwaregerichte afstemming.","2025-11-12T14:48:37","why-cuda-translation-wont-unlock-amds-real-potential","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Fchatgpt-image-nov-11-2025-09_16_10-pm-1.webp","https:\u002F\u002Feliovp.com\u002Fwhy-cuda-translation-wont-unlock-amds-real-potential\u002F",[562,563,183,564,565,563,902,903,904,905,906,907,183,908],"CUDA-vertaling","FP8","GPU-optimalisatie","High-performance computing","HIP","Kerneltuning","ROCm",{"path":910,"title":911,"description":912,"date":913,"slug":914,"image":915,"originalUrl":916,"categories":917},"\u002Fblog\u002Fpaiton-the-simplest-way-to-supercharge-ai-inference","Paiton: snellere AI-inferentie in uw bestaande stack","Lees hoe Paiton aansluit op bestaande inferentiestacks, met AMD MI300X-benchmarks en vergelijkingen van prestaties per dollar.","2025-11-11T10:31:22","paiton-the-simplest-way-to-supercharge-ai-inference","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Fpaiton-powaaah.webp","https:\u002F\u002Feliovp.com\u002Fpaiton-the-simplest-way-to-supercharge-ai-inference\u002F",[562,563,183,611,610,565,737,918,694,907,183,919,695],"Hoge throughput","SGLang",{"path":921,"title":922,"description":923,"date":924,"slug":925,"image":926,"originalUrl":927,"categories":928},"\u002Fblog\u002Fstop-overpaying-paiton-mi300x-moe-beats-h200-b200-on-1m-tokens","Paiton MoE-benchmarks: MI300X versus H200 en B200","Vergelijk Qwen3-30B-A3B MoE-benchmarks van MI300X met Paiton, H200 en B200: throughput en kosten per miljoen tokens.","2025-09-26T13:36:18","stop-overpaying-paiton-mi300x-moe-beats-h200-b200-on-1m-tokens","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Fhulkvshulkpaitonwins.webp","https:\u002F\u002Feliovp.com\u002Fstop-overpaying-paiton-mi300x-moe-beats-h200-b200-on-1m-tokens\u002F",[562,563,183,929,565,930,694,931,932,933,934,183,935],"AI-benchmarks","Kosten per token","Mixture of Experts","MoE","NVIDIA B200","NVIDIA H200","Qwen3",{"path":937,"title":938,"description":939,"date":940,"slug":941,"image":942,"originalUrl":943,"categories":944},"\u002Fblog\u002Fagentic-ai-but-make-it-local-from-inbox-to-insight-to-action-en","Lokale Agentic AI: van inbox naar actie","Lokale AI-agents zetten e-mails, documenten en beelden om in tickets, rapporten en acties, met modellen op maat van uw gegevens en systemen.","2025-09-16T13:09:00","agentic-ai-but-make-it-local-from-inbox-to-insight-to-action-en","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Ffrontfotoblog.webp","https:\u002F\u002Feliovp.com\u002Fagentic-ai-but-make-it-local-from-inbox-to-insight-to-action-en\u002F",[562,563,848,564,849,945,946,947,948,853,855,782,949,950],"Schadedetectie","Documentverwerking","E-mailautomatisering","Factuurextractie","Ticketautomatisering","Workflowautomatisering",{"path":952,"title":953,"description":954,"date":955,"slug":956,"image":957,"originalUrl":958,"categories":959},"\u002Fblog\u002Fmi300x-fp8-data-parallel-benchmarks-8-64-gpus-h200-left-behind-b200-within-reach","MI300X FP8-benchmarks: GPU-partitionering met Paiton","Bekijk hoe Paiton presteert met Llama 3.1 8B FP8 op gepartitioneerde MI300X-GPU's, vergeleken met NVIDIA H200 en B200.","2025-07-31T13:32:57","mi300x-fp8-data-parallel-benchmarks-8-64-gpus-h200-left-behind-b200-within-reach","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Fimage-2-1.webp","https:\u002F\u002Feliovp.com\u002Fmi300x-fp8-data%e2%80%91parallel-benchmarks-8-64-gpus-h200-left-behind-b200-within-reach\u002F",[562,563,183,564,960,768,769,468,961,779,645,183,695],"AI","MI300X",{"path":963,"title":964,"description":965,"date":966,"slug":967,"image":968,"originalUrl":969,"categories":970},"\u002Fblog\u002Fapplicable-ai-for-businesses","Toepasbare AI voor bedrijven","Ontdek hoe ElioVP lokale AI voor bedrijfsprocessen bouwt, met modeltraining op maat en automatische schadedetectie voor de logistiek.","2025-07-09T21:35:30","applicable-ai-for-businesses","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Fscherm_afbeelding-2025-07-09-om-23.30.17.webp","https:\u002F\u002Feliovp.com\u002Fapplicable-ai-for-businesses\u002F",[562,563,848,849,945,946,947,948,853,855,782,949,950],{"path":972,"title":973,"description":974,"date":975,"slug":976,"image":480,"originalUrl":977,"categories":978},"\u002Fblog\u002Fintroducing-paitons-free-evaluation-models","Maak kennis met de gratis evaluatiemodellen van Paiton","Test Paiton met gratis evaluatiemodellen voor AMD-GPU's. Vergelijk de prestaties voor tekst, beeldanalyse en beeldgeneratie met uw eigen workloads.","2025-07-07T11:26:13","introducing-paitons-free-evaluation-models","https:\u002F\u002Feliovp.com\u002Fintroducing-paitons-free-evaluation-models\u002F",[562,563,183],{"path":980,"title":981,"description":982,"date":983,"slug":984,"image":985,"originalUrl":986,"categories":987},"\u002Fblog\u002Fpaiton-dramatically-faster-startup-and-performance-for-llama-3-1-405b","Llama 3.1 405B: sneller starten met Paiton op MI300X","Bekijk Paiton-benchmarks voor Llama 3.1 405B op acht AMD MI300X-GPU's, met opstarttijd, tensorparallelisme, throughput en latency.","2025-06-12T20:15:23","paiton-dramatically-faster-startup-and-performance-for-llama-3-1-405b","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Fservingscreenshot.webp","https:\u002F\u002Feliovp.com\u002Fpaiton-dramatically-faster-startup-and-performance-for-llama-3-1-405b\u002F",[562,563,183,564,611,565,988,903,989,572,990,183,991,992],"Koude start","Grafiekcompilatie","LLM-optimalisatie","Opstartlatentie","Tensor-parallellisme",{"path":583,"title":5,"description":576,"date":575,"slug":585,"image":579,"originalUrl":582,"categories":994},[562,563,183,564,565,566,567,568,569,570,571,572,573,574],{"path":996,"title":997,"description":998,"date":999,"slug":1000,"image":1001,"originalUrl":1002,"categories":1003},"\u002Fblog\u002Fmi300x-vs-h200-vs-rx-7900-xtx-vs-tenstorrent-n300s-with-vllm","MI300X, H200, RX 7900 XTX en n300s: vLLM-benchmarks","Vergelijk MI300X, H200, RX 7900 XTX en Tenstorrent n300s met vLLM: throughput, gemodelleerde tokenkosten en hardwarebeperkingen voor Llama 3 8B.","2025-05-09T14:03:58","mi300x-vs-h200-vs-rx-7900-xtx-vs-tenstorrent-n300s-with-vllm","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Fcomparisontenstor.webp","https:\u002F\u002Feliovp.com\u002Fmi300x-vs-h200-vs-rx-7900-xtx-vs-tenstorrent-n300s-with-vllm\u002F",[562,563,183,848,564,768,961,645,1004,1005],"RX7900XTX","tenstorrent",{"path":1007,"title":1008,"description":1009,"date":1010,"slug":1011,"image":1012,"originalUrl":1013,"categories":1014},"\u002Fblog\u002Fclusterpl-empowering-gpu-cluster-investors-with-real-world-financial-insights","ClusterP&L: financiële modellen voor GPU-clusters","Ontdek hoe ClusterP&L kosten, rendement en investeringsscenario's voor GPU-clusters modelleert, met risicoanalyses en exporteerbare rapporten.","2025-05-03T10:52:22","clusterpl-empowering-gpu-cluster-investors-with-real-world-financial-insights","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Fcomparisonscenarios.webp","https:\u002F\u002Feliovp.com\u002Fclusterpl-empowering-gpu-cluster-investors-with-real-world-financial-insights\u002F",[562,563,797,848,769,468,1015,645,1016],"MI325X","P&L-calculator",{"path":1018,"title":1019,"description":1020,"date":1021,"slug":1022,"image":1023,"originalUrl":1024,"categories":1025},"\u002Fblog\u002Fcranking-out-faster-tokens-for-fewer-dollars-amd-mi300x-vs-nvidia-h200","AMD MI300X versus NVIDIA H200: Qwen3-32B met Paiton","Vergelijk Qwen3-32B-benchmarks op AMD MI300X met Paiton en NVIDIA H200, met resultaten voor throughput, latency en hardwarekosten.","2025-05-02T21:10:30","cranking-out-faster-tokens-for-fewer-dollars-amd-mi300x-vs-nvidia-h200","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002F3ac59a73-2466-4422-b7e5-ef2e4a8ca58e.webp","https:\u002F\u002Feliovp.com\u002Fcranking-out-faster-tokens-for-fewer-dollars-amd-mi300x-vs-nvidia-h200\u002F",[562,563,183,960,768,468,1026,645,183,695],"MI300",{"path":1028,"title":1029,"description":1030,"date":1031,"slug":1032,"image":1033,"originalUrl":1034,"categories":1035},"\u002Fblog\u002Fpower-meets-precision-high-density-modular-data-center-for-nvidia-nvl-deployments-1-2-mw","Modulaire datacenters voor NVIDIA NVL: 1 tot 2 MW","Ontdek modulaire datacenterontwerpen voor NVIDIA NVL-systemen, met aandacht voor vermogen, vloeistofkoeling, redundantie en uitrolplanning.","2025-05-02T14:09:59","power-meets-precision-high-density-modular-data-center-for-nvidia-nvl-deployments-1-2-mw","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Feliovp_critical-1mw-pod_rev-2_transparent.webp","https:\u002F\u002Feliovp.com\u002Fpower-meets-precision-high-density-modular-data-center-for-nvidia-nvl-deployments-1-2-mw\u002F",[562,797,1036,866,887,756,647,888,1037,1038,891,1039],"1-2MW datacenter","NVIDIA Blackwell","NVIDIA NVL","Precisiekoeling",{"path":1041,"title":1042,"description":1043,"date":1044,"slug":1045,"image":1046,"originalUrl":1047,"categories":1048},"\u002Fblog\u002Fexamining-ai-agents-in-the-medical-field-ai-that-speaks-dicom","AI-agents in de medische wereld: AI die DICOM spreekt","Ontdek een lokale AI-agent die DICOM-gegevens opzoekt en bekijk tests van beeldmodellen met geanonimiseerde medische beelden.","2025-04-11T14:45:48","examining-ai-agents-in-the-medical-field-ai-that-speaks-dicom","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Fhealthcareblog-1.webp","https:\u002F\u002Feliovp.com\u002Fexamining-ai-agents-in-the-medical-field-ai-that-speaks-dicom\u002F",[562,563,848,564,960,768,1049],"Zorg",{"path":1051,"title":1052,"description":1053,"date":1054,"slug":1055,"image":1056,"originalUrl":1057,"categories":1058},"\u002Fblog\u002Feliovp-bv-your-trusted-partner-for-supply-chain-resilience-amidst-new-u-s-tariffs","Amerikaanse invoerheffingen en AI-leveringszekerheid in 2025","Lees ElioVP's visie uit april 2025 op Amerikaanse invoerheffingen en leveringszekerheid voor AI-servers, HPC-systemen en modulaire datacenters.","2025-04-04T10:01:27","eliovp-bv-your-trusted-partner-for-supply-chain-resilience-amidst-new-u-s-tariffs","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Ftariffsshipping.webp","https:\u002F\u002Feliovp.com\u002Feliovp-bv-your-trusted-partner-for-supply-chain-resilience-amidst-new-u-s-tariffs\u002F",[562,808,960,768,1059,1060,1061,1062],"Invoer","Taiwan","Invoerheffingen","Trump",{"path":1064,"title":1065,"description":1066,"date":1067,"slug":1068,"image":1069,"originalUrl":1070,"categories":1071},"\u002Fblog\u002Fwhy-ai-agents-are-the-future","Waarom AI-agenten de toekomst zijn","Ontdek AI-agents voor ERP, CRM, financiën en klantondersteuning, met praktijkvoorbeelden en een traject van procesanalyse tot pilot en uitrol.","2025-03-23T22:06:59","why-ai-agents-are-the-future","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Ferp2.jpeg","https:\u002F\u002Feliovp.com\u002Fwhy-ai-agents-are-the-future\u002F",[562,563,848,960,1072,1073],"AI-agenten","ERP",{"path":1075,"title":1076,"description":1077,"date":1078,"slug":1079,"image":1080,"originalUrl":1081,"categories":1082},"\u002Fblog\u002Fthe-rise-of-open-source-ai-model-optimization","De opkomst van open-source AI-modeloptimalisatie","Verken trends in opensource-AI-optimalisatie: kwantisatie, mixture-of-experts-modellen, hardwaregerichte afstemming, RAG en edge-AI.","2025-03-22T20:59:23","the-rise-of-open-source-ai-model-optimization","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Friseofopensource.jpeg","https:\u002F\u002Feliovp.com\u002Fthe-rise-of-open-source-ai-model-optimization\u002F",[562,563,808,1083,768,775,645],"AI-nieuws",{"path":1085,"title":1086,"description":1087,"date":1088,"slug":1089,"image":1090,"originalUrl":1091,"categories":1092},"\u002Fblog\u002Fintroducing-our-benchmarking-tool-powered-by-dstack","Maak kennis met onze benchmarktool, gebouwd op dstack","Ontdek onze benchmarktool met dstack: herhaalbare vLLM-tests, automatische parameterreeksen en prestatierapporten voor lokale GPU's en de cloud.","2025-03-20T14:21:59","introducing-our-benchmarking-tool-powered-by-dstack","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Fbenchmarktool.jpeg","https:\u002F\u002Feliovp.com\u002Fintroducing-our-benchmarking-tool-powered-by-dstack\u002F",[562,563,183,960,768,1093,1094,961,183],"benchmark","LLM",{"path":1096,"title":1097,"description":1098,"date":1099,"slug":1100,"image":1101,"originalUrl":1102,"categories":1103},"\u002Fblog\u002Foptimizing-qwq-32b-by-qwen-amd-mi300x-vs-nvidia-h200","QwQ-32B optimaliseren (door Qwen): AMD MI300X versus NVIDIA H200","Vergelijk throughput en latency van QwQ-32B op AMD MI300X met Paiton en NVIDIA H200, bij kleine batches en meer gelijktijdige aanvragen.","2025-03-19T21:41:44","optimizing-qwq-32b-by-qwen-amd-mi300x-vs-nvidia-h200","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Fpaiton4.jpeg","https:\u002F\u002Feliovp.com\u002Foptimizing-qwq-32b-by-qwen-amd-mi300x-vs-nvidia-h200\u002F",[562,563,183],{"path":1105,"title":1106,"description":1107,"date":1108,"slug":1109,"image":1110,"originalUrl":1111,"categories":1112},"\u002Fblog\u002Feliovp-featured-on-amd-tech-talk-podcast","Eliovp te gast in de AMD Tech Talk-podcast","Beluister Elio Van Puyvelde en Jim Greene in de AMD Tech Talk-podcast over het ontstaan van ElioVP en de hardware- en softwarediensten voor AI.","2025-03-19T07:53:39","eliovp-featured-on-amd-tech-talk-podcast","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Ftechtalkjimgreene.jpeg","https:\u002F\u002Feliovp.com\u002Feliovp-featured-on-amd-tech-talk-podcast\u002F",[562,768,1113,1114,1115],"Jim Greene","Podcast","Tech Talk",{"path":1117,"title":1118,"description":1119,"date":1120,"slug":1121,"image":1122,"originalUrl":1123,"categories":1124},"\u002Fblog\u002Ffurther-optimizing-amd-powered-inference-with-paiton","AMD-inferentie verder optimaliseren met Paiton","Bekijk Paiton-benchmarks voor DeepSeek R1 Distill Llama 8B op AMD MI300X, gericht op throughput en latency bij kleinere batchgroottes.","2025-03-13T06:18:30","further-optimizing-amd-powered-inference-with-paiton","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Fpaitonpost3.webp","https:\u002F\u002Feliovp.com\u002Ffurther-optimizing-amd-powered-inference-with-paiton\u002F",[562,563,183,768,612,1125,468,961,1015,183,695],"H100",{"path":1127,"title":1128,"description":1129,"date":1130,"slug":1131,"image":1132,"originalUrl":1133,"categories":1134},"\u002Fblog\u002Fa-first-look-at-paiton-in-action-deepseek-r1-distill-llama-3-1-8b","Paiton-benchmarks: DeepSeek R1 Distill Llama 3.1 8B","Vergelijk standaard- en Paiton-versies van DeepSeek R1 Distill Llama 3.1 8B op AMD MI300X, met benchmarks voor throughput en latency.","2025-01-31T09:11:02","a-first-look-at-paiton-in-action-deepseek-r1-distill-llama-3-1-8b","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Fpaitonpost2.webp","https:\u002F\u002Feliovp.com\u002Fa-first-look-at-paiton-in-action-deepseek-r1-distill-llama-3-1-8b\u002F",[562,563,183,768,612,1125,468,961,1015,183,695],{"path":1136,"title":1137,"description":1138,"date":1139,"slug":1140,"image":1141,"originalUrl":1142,"categories":1143},"\u002Fblog\u002Fai-model-optimization-with-paiton","AI-modeloptimalisatie met Paiton","Lees hoe Paiton modelcompilatie, aangepaste kernels en kernelfusie inzet om AI-inferentie op AMD GPU's te optimaliseren.","2025-01-30T19:53:25","ai-model-optimization-with-paiton","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Fpaitonpost1.webp","https:\u002F\u002Feliovp.com\u002Fai-model-optimization-with-paiton\u002F",[562,563,183,768,1125,468,961,1015,183,695],1793962345758]