[{"data":1,"prerenderedAt":675},["ShallowReactive",2],{"blog-post-nl-\u002Fblog\u002Ffrom-the-attic-to-the-front-page-eliovp-recognized-as-a-pioneer-in-chip-optimization-data-center-infrastructure":3,"blog-posts-sidebar-nl":198},{"id":4,"title":5,"body":6,"categories":178,"date":185,"description":186,"extension":187,"heading":188,"image":50,"meta":189,"navigation":190,"originalUrl":191,"path":192,"seo":193,"slug":194,"stem":195,"updated":196,"__hash__":197},"blogNl\u002Fblog\u002Ffrom-the-attic-to-the-front-page-eliovp-recognized-as-a-pioneer-in-chip-optimization-data-center-infrastructure.md","ElioVP in De Tijd: chipoptimalisatie en datacenters",{"type":7,"value":8,"toc":170},"minimark",[9,35,42,45,51,58,65,71,76,90,96,102,108,115,121,127,130,140,143,149,155,158],[10,11,12,13,17,18,21,22,34],"p",{},"Het waren bijzondere weken voor het team van ",[14,15,16],"strong",{},"Eliovp",". We zijn enorm trots dat ons bedrijf onlangs de ",[14,19,20],{},"voorpagina van"," ",[23,24,28],"a",{"href":25,"rel":26},"https:\u002F\u002Fwww.tijd.be\u002F",[27],"nofollow",[29,30,31],"em",{},[14,32,33],{},"De Tijd"," haalde, de toonaangevende zakenkrant van België.",[10,36,37],{},[38,39],"img",{"alt":40,"src":41},"De oprichter van ElioVP met de voorpagina van De Tijd in het serverpad van een modulair datacenter","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Fvettefotoschuin.jpg",[10,43,44],{},"Ons verhaal begon bij een oprichter die op zolder aan hardware sleutelde en groeide uit tot een onderneming met 215 miljoen euro omzet. Dat verhaal in grote letters op de voorpagina van de papieren krant zien staan, was een echte mijlpaal. Het is een erkenning van het harde werk van ons team en van onze onophoudelijke drang om alle mogelijke prestaties uit moderne hardware te halen.",[10,46,47],{},[38,48],{"alt":49,"src":50},"","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Fphysicalnewspaper.webp",[52,53,55],"h3",{"id":54},"de-race-om-efficiëntie",[14,56,57],{},"De race om efficiëntie",[10,59,60,61,64],{},"Het hoofdartikel, getiteld ",[29,62,63],{},"“Vlaams bedrijf optimaliseert chips van AMD en Nvidia en draait daarmee 215 miljoen euro omzet,”"," gaat uitgebreid in op onze oorsprong.",[10,66,67,68],{},"Zoals het artikel benadrukt, begonnen we met het ontsluiten van het verborgen potentieel in hardware van spelers zoals AMD en NVIDIA. Door software te optimaliseren en standaard fabrieksbeperkingen te omzeilen, leverden we de snelheid en efficiëntie waar de crypto- en AI-markten dringend behoefte aan hadden. Zoals onze oprichter Elio Van Puyvelde tegen de krant zei: ",[29,69,70],{},"“In de race naar efficiëntie is mijn oplossing goud waard.”",[10,72,73],{},[38,74],{"alt":49,"src":75},"\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Fderace.jpg",[10,77,78,21,81,21,87],{},[29,79,80],{},"(Het volledige online artikel kunt u hier lezen:",[23,82,85],{"href":83,"rel":84},"https:\u002F\u002Fwww.tijd.be\u002Fondernemen\u002Ftechnologie\u002Fvlaams-bedrijf-optimaliseert-chips-van-amd-en-nvidia-en-draait-daarmee-215-miljoen-euro-omzet\u002F10635877.html",[27],[29,86,33],{},[29,88,89],{},")",[52,91,93],{"id":92},"bouwen-aan-de-infrastructuur-van-de-toekomst",[14,94,95],{},"Bouwen aan de infrastructuur van de toekomst",[10,97,98,99,101],{},"Hoewel we bekendstaan om software-optimalisatie, bleef de berichtgeving daar niet bij. We zijn bijzonder trots op de vervolganalyse die ",[29,100,33],{}," een week later publiceerde over de snelgroeiende datacentersector.",[10,103,104,105],{},"Naarmate AI-modellen groter worden, krijgen traditionele datacenters het moeilijk met de enorme warmte- en vermogensdichtheid van moderne GPU's. We beseften al vroeg dat we de chips niet alleen moesten optimaliseren om de volgende generatie computing mogelijk te maken. ",[14,106,107],{},"We moesten ook de omgeving bouwen waarin die chips draaien.",[10,109,110,111,114],{},"Daarom zijn we ons veel sterker gaan toeleggen op het ontwerpen en bouwen van ",[14,112,113],{},"modulaire datacenters",". Dit zijn geen gewone serverruimtes, maar hoogwaardige geprefabriceerde modules die ontworpen zijn voor de extreme vermogensdichtheden van de AI-revolutie.",[10,116,117],{},[38,118],{"alt":119,"src":120},"De Tijd artikel met ElioVP als standaardsetter in modulaire datacenterbouw","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Fenglishversionprofitereboomdatacenter.jpg",[52,122,124],{"id":123},"de-norm-bepalen-in-de-sector",[14,125,126],{},"De norm bepalen in de sector",[10,128,129],{},"Waar we misschien nog het meest trots op zijn, is dat ElioVP niet alleen werd erkend als deelnemer aan deze markt, maar ook als pionier.",[10,131,132,133,136,137,139],{},"In het vervolgartikel ",[29,134,135],{},"“Belgische bedrijven profiteren van boom datacenters,”"," beschrijft ",[29,138,33],{}," hoe het Vlaamse datacenterecosysteem snel groeit. We zijn vereerd dat de krant ElioVP als pionier in dit domein noemt en opmerkt dat onze vroege innovaties mee de weg hebben vrijgemaakt voor andere lokale spelers die nu de markt betreden.",[10,141,142],{},"Het is een voorrecht om te zien dat onze gespecialiseerde benadering van modulaire constructie en koeling met hoge dichtheid een blauwdruk is geworden voor de industrie. We zijn er trots op dat we hier in België een sterk technologie-ecosysteem zien groeien, met ElioVP in de voorhoede.",[52,144,146],{"id":145},"vooruitkijken",[14,147,148],{},"Vooruitkijken",[10,150,151,152,154],{},"We willen de redactie van ",[29,153,33],{},", en in het bijzonder Emma Verplancke, van harte bedanken voor het vertellen van ons verhaal. Ook fotograaf Jonas Lampens bedanken we voor de fantastische beelden.",[10,156,157],{},"Het belangrijkste is dat we onze partners en ons team willen bedanken. Of we nu een enkele GPU optimaliseren of een modulair datacenter inzetten om het volgende grote taalmodel te trainen, ElioVP streeft ernaar voorop te blijven lopen.",[10,159,160,21,163],{},[29,161,162],{},"Lees hier het vervolgartikel over datacenters:",[23,164,167],{"href":165,"rel":166},"https:\u002F\u002Fwww.tijd.be\u002Fondernemen\u002Fict\u002Fbelgische-bedrijven-profiteren-van-boom-datacenters-vroeger-maakten-we-grondstof-voor-zeep-nu-koelen-we-servers\u002F10646132.html",[27],[29,168,169],{},"De Tijd – Datacenter Boom",{"title":49,"searchDepth":171,"depth":171,"links":172},2,[173,175,176,177],{"id":54,"depth":174,"text":57},3,{"id":92,"depth":174,"text":95},{"id":123,"depth":174,"text":126},{"id":145,"depth":174,"text":148},[179,180,181,182,183,33,181,184],"Alle","Kunstmatige intelligentie","Modulaire DC","Niet gecategoriseerd","AMD","NVIDIA","2026-02-10T20:48:12","Lees hoe De Tijd ElioVP belicht, van de oorsprong in chipoptimalisatie tot het werk aan modulaire datacenters en koeling voor hoge vermogensdichtheid.","md","Van zolder tot voorpagina: ElioVP erkend als pionier op het gebied van chipoptimalisatie en datacenterinfrastructuur",{},true,"https:\u002F\u002Feliovp.com\u002Ffrom-the-attic-to-the-front-page-eliovp-recognized-as-a-pioneer-in-chip-optimization-data-center-infrastructure\u002F","\u002Fblog\u002Ffrom-the-attic-to-the-front-page-eliovp-recognized-as-a-pioneer-in-chip-optimization-data-center-infrastructure",{"title":5,"description":186},"from-the-attic-to-the-front-page-eliovp-recognized-as-a-pioneer-in-chip-optimization-data-center-infrastructure","blog\u002Ffrom-the-attic-to-the-front-page-eliovp-recognized-as-a-pioneer-in-chip-optimization-data-center-infrastructure",null,"cHBE9374Lv-w4YbEuk56nM-jSbcV__VaewdOFY2LKIQ",[199,215,225,237,248,260,269,282,311,313,335,353,372,391,409,426,438,454,469,481,490,498,513,525,536,547,557,570,580,593,604,614,625,634,646,657,666],{"path":200,"title":201,"description":202,"date":203,"slug":204,"image":205,"originalUrl":206,"categories":207},"\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",[208,209,210,211,212,213,214],"Paiton","AMD Radeon","Lokale AI","AI-inferentie","Inferentie-optimalisatie","Grote taalmodellen","vLLM",{"path":216,"title":217,"description":218,"date":219,"slug":220,"image":221,"originalUrl":222,"categories":223},"\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",[208,209,210,224,214],"GGUF",{"path":226,"title":227,"description":228,"date":229,"slug":230,"image":231,"originalUrl":232,"categories":233},"\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",[208,209,210,234,235,236],"Videogeneratie","MiniMax H3","ComfyUI",{"path":238,"title":239,"description":240,"date":241,"slug":242,"image":243,"originalUrl":244,"categories":245},"\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",[208,209,210,246,247,236],"Beeldgeneratie","FLUX",{"path":249,"title":250,"description":251,"date":252,"slug":253,"image":254,"originalUrl":255,"categories":256},"\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",[208,180,209,211,257,258,212,213,214,259],"GPU-prestaties","Inferentielatentie","Kostenefficiëntie",{"path":261,"title":262,"description":263,"date":264,"slug":265,"image":266,"originalUrl":267,"categories":268},"\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",[208,180,209,211,257,258,212,213,214,259],{"path":270,"title":271,"description":272,"date":273,"slug":274,"image":275,"originalUrl":196,"categories":276},"\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",[179,277,278,279,280,281],"AI-infrastructuur","Datacenters","ModFlex","HPC","AMD Helios",{"path":283,"title":284,"description":285,"date":286,"slug":287,"image":288,"originalUrl":289,"categories":290},"\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",[179,180,208,291,183,292,293,294,295,296,16,297,298,299,300,301,302,184,303,304,208,305,306,307,308,309,310],"14B","B200","Benchmarks","Blackwell","Compute","Diffusie","Generatieve AI","GPU","Hardware","Inferentie","Instinct","MI355x","On-premises","Optimalisatie","Soevereine AI","T2V","Tekst-naar-video","Tuning","Video-generatie","Wan2.2",{"path":192,"title":5,"description":186,"date":185,"slug":194,"image":50,"originalUrl":191,"categories":312},[179,180,181,182,183,33,181,184],{"path":314,"title":315,"description":316,"date":317,"slug":318,"image":319,"originalUrl":320,"categories":321},"\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",[179,180,322,182,323,324,325,326,327,328,329,330,16,331,297,332,333,334],"Trending","AI Act","Antropomorfisme","AVG","Benelux","ChatGPT","Cyberbeveiliging","Databeheer","Gegevensbeveiliging","GDPR","Microsoft Copilot","Privacy","Shadow AI",{"path":336,"title":337,"description":338,"date":339,"slug":340,"image":341,"originalUrl":342,"categories":343},"\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",[179,344,345,346,328,347,348,349,331,350,351,352,333],"AWS","Belgian Mobile ID","CLOUD Act","Datasoevereiniteit","Digitale identiteit","eIDAS","itsme","Liberty Global","MyGov.be",{"path":354,"title":355,"description":356,"date":357,"slug":358,"image":359,"originalUrl":360,"categories":361},"\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",[179,180,362,322,363,364,365,366,367,368,369,370,305,371],"Oplossingen","Agentic AI","AI-techniek","AI-strategie","Autonome agenten","Bedrijfs-AI","Lokale LLM","Modelverfijning","AI op locatie","VRAM-optimalisatie",{"path":373,"title":374,"description":375,"date":376,"slug":377,"image":378,"originalUrl":379,"categories":380},"\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",[179,180,322,381,382,383,384,385,386,387,388,389,390],"AI Infrastructure","AI Neocloud","Circulaire financiering","GPU Cloud","Beleggingsrisico's","Opstartwaardering","Synthetische bubbel","Technische analyse","Vaporware","Durfkapitaal",{"path":392,"title":393,"description":394,"date":395,"slug":396,"image":397,"originalUrl":398,"categories":399},"\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",[179,181,182,400,277,401,402,403,404,405,406,407,408],"150 kW-rack","DLC","Hoge dichtheid","Vloeistofkoeling","Modulair datacenter","NVIDIA Blackwell Ultra","NVIDIA GB300","NVL72","Snelle implementatie",{"path":410,"title":411,"description":412,"date":413,"slug":414,"image":415,"originalUrl":416,"categories":417},"\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",[179,180,208,182,418,180,419,420,421,422,423,424,208,425],"AMD MI300X","CUDA-vertaling","FP8","GPU-optimalisatie","High-performance computing","HIP","Kerneltuning","ROCm",{"path":427,"title":428,"description":429,"date":430,"slug":431,"image":432,"originalUrl":433,"categories":434},"\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",[179,180,208,211,435,418,259,436,212,424,208,437,214],"AMD Instinct","Hoge throughput","SGLang",{"path":439,"title":440,"description":441,"date":442,"slug":443,"image":444,"originalUrl":445,"categories":446},"\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",[179,180,208,447,418,448,212,449,450,451,452,208,453],"AI-benchmarks","Kosten per token","Mixture of Experts","MoE","NVIDIA B200","NVIDIA H200","Qwen3",{"path":455,"title":456,"description":457,"date":458,"slug":459,"image":460,"originalUrl":461,"categories":462},"\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",[179,180,362,182,363,463,464,465,466,368,370,305,467,468],"Schadedetectie","Documentverwerking","E-mailautomatisering","Factuurextractie","Ticketautomatisering","Workflowautomatisering",{"path":470,"title":471,"description":472,"date":473,"slug":474,"image":475,"originalUrl":476,"categories":477},"\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",[179,180,208,182,478,183,292,479,480,302,184,208,214],"AI","H200","MI300X",{"path":482,"title":483,"description":484,"date":485,"slug":486,"image":487,"originalUrl":488,"categories":489},"\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",[179,180,362,363,463,464,465,466,368,370,305,467,468],{"path":491,"title":492,"description":493,"date":494,"slug":495,"image":49,"originalUrl":496,"categories":497},"\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",[179,180,208],{"path":499,"title":500,"description":501,"date":502,"slug":503,"image":504,"originalUrl":505,"categories":506},"\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",[179,180,208,182,211,418,507,420,508,509,510,208,511,512],"Koude start","Grafiekcompilatie","Llama 3.1 405B","LLM-optimalisatie","Opstartlatentie","Tensor-parallellisme",{"path":514,"title":515,"description":516,"date":517,"slug":518,"image":519,"originalUrl":520,"categories":521},"\u002Fblog\u002Fpaiton-fp8-beats-nvidias-h200-on-amds-mi300x","Paiton FP8 verslaat NVIDIA's H200 op AMD's MI300X","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.","2025-06-08T19:12:40","paiton-fp8-beats-nvidias-h200-on-amds-mi300x","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Fblognewfp8.webp","https:\u002F\u002Feliovp.com\u002Fpaiton-fp8-beats-nvidias-h200-on-amds-mi300x\u002F",[179,180,208,182,418,522,367,297,257,258,213,509,523,524],"Koude startoptimalisatie","Model serving","vLLM-optimalisatie",{"path":526,"title":527,"description":528,"date":529,"slug":530,"image":531,"originalUrl":532,"categories":533},"\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",[179,180,208,362,182,183,480,184,534,535],"RX7900XTX","tenstorrent",{"path":537,"title":538,"description":539,"date":540,"slug":541,"image":542,"originalUrl":543,"categories":544},"\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",[179,180,181,362,292,479,545,184,546],"MI325X","P&L-calculator",{"path":548,"title":549,"description":550,"date":551,"slug":552,"image":553,"originalUrl":554,"categories":555},"\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",[179,180,208,478,183,479,556,184,208,214],"MI300",{"path":558,"title":559,"description":560,"date":561,"slug":562,"image":563,"originalUrl":564,"categories":565},"\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",[179,181,566,381,402,280,403,404,567,568,407,569],"1-2MW datacenter","NVIDIA Blackwell","NVIDIA NVL","Precisiekoeling",{"path":571,"title":572,"description":573,"date":574,"slug":575,"image":576,"originalUrl":577,"categories":578},"\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",[179,180,362,182,478,183,579],"Zorg",{"path":581,"title":582,"description":583,"date":584,"slug":585,"image":586,"originalUrl":587,"categories":588},"\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",[179,322,478,183,589,590,591,592],"Invoer","Taiwan","Invoerheffingen","Trump",{"path":594,"title":595,"description":596,"date":597,"slug":598,"image":599,"originalUrl":600,"categories":601},"\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",[179,180,362,478,602,603],"AI-agenten","ERP",{"path":605,"title":606,"description":607,"date":608,"slug":609,"image":610,"originalUrl":611,"categories":612},"\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",[179,180,322,613,183,298,184],"AI-nieuws",{"path":615,"title":616,"description":617,"date":618,"slug":619,"image":620,"originalUrl":621,"categories":622},"\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",[179,180,208,478,183,623,624,480,208],"benchmark","LLM",{"path":626,"title":627,"description":628,"date":629,"slug":630,"image":631,"originalUrl":632,"categories":633},"\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",[179,180,208],{"path":635,"title":636,"description":637,"date":638,"slug":639,"image":640,"originalUrl":641,"categories":642},"\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",[179,183,643,644,645],"Jim Greene","Podcast","Tech Talk",{"path":647,"title":648,"description":649,"date":650,"slug":651,"image":652,"originalUrl":653,"categories":654},"\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",[179,180,208,183,655,656,479,480,545,208,214],"DeepSeek","H100",{"path":658,"title":659,"description":660,"date":661,"slug":662,"image":663,"originalUrl":664,"categories":665},"\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",[179,180,208,183,655,656,479,480,545,208,214],{"path":667,"title":668,"description":669,"date":670,"slug":671,"image":672,"originalUrl":673,"categories":674},"\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",[179,180,208,183,656,479,480,545,208,214],1789853167192]