[{"data":1,"prerenderedAt":1146},["ShallowReactive",2],{"blog-post-en-\u002Fblog\u002Fpaiton-fp8-beats-nvidias-h200-on-amds-mi300x":3,"blog-posts-sidebar-en":589},{"id":4,"title":5,"body":6,"categories":562,"date":576,"description":577,"extension":578,"heading":579,"image":580,"meta":581,"navigation":582,"originalUrl":583,"path":584,"seo":585,"slug":586,"socialImage":579,"stem":587,"updated":579,"video":579,"__hash__":588},"blog\u002Fblog\u002Fpaiton-fp8-beats-nvidias-h200-on-amds-mi300x.md","Paiton FP8 Beats NVIDIA’s H200 on AMD’s MI300X",{"type":7,"value":8,"toc":554},"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",{},"The world of AI is moving at an unprecedented pace, and efficient inference is key to deploying powerful models in real-world applications. At Eliovp, we’ve consistently pushed the boundaries of AI performance, as highlighted in our previous blogs showcasing significant inference speedups when benchmarking with fp16\u002Fbf16. Now, we’re thrilled to announce a further significant leap forward: Paiton now achieves superior inference performance on AMD MI300X GPUs with FP8, outperforming NVIDIA’s H200. While both AMD and NVIDIA support FP8, our meticulously optimized kernels deliver these breakthrough results.",[10,14,15],{},"For too long, the narrative around AI hardware has been dominated by a single player. However, AMD’s MI300 series is a game-changer, offering incredible compute power. The challenge, as always, lies in extracting every ounce of that power. That’s where Paiton comes in.",[10,17,18],{},"Our core mission at Paiton is to optimize existing AI models by fine-tuning the kernels used for inference, with a specific focus on AMD architectures. We dive deep into the underlying operations, rewriting, fusing, and refining them to perfectly align with the unique strengths of AMD’s hardware. The result? Dramatically faster inference speeds and more efficient resource utilization.",[20,21,23],"h3",{"id":22},"testbed-methodology",[24,25,26],"strong",{},"Testbed & Methodology",[10,28,29],{},"To ensure transparency and reproducibility, here’s our benchmarking setup:",[10,31,32],{},"As always, we made sure to use the best possible setup to keep things fair.",[34,35,36,50,56,62,68],"ul",{},[37,38,39,42,43],"li",{},[24,40,41],{},"Inference Library:"," 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 (192 GB HBM3) vs. NVIDIA H200 (141GB HBM3e)",[37,57,58,61],{},[24,59,60],{},"Software Stack:"," ROCm 6.3.1 (we know we can get even better results when upgrading to 6.4) on Ubuntu 22.04; CUDA 12.x on Ubuntu 22.04",[37,63,64,67],{},[24,65,66],{},"Measurements:"," Averaged over 10 inferences, capturing both cold-start and steady-state Time to First Token (TTFT) and end-to-end latency (API call → final token).",[37,69,70,73],{},[24,71,72],{},"Batch Sizes:"," 1–128 to reflect interactive AI loads (1–64) vs. batch-processing extremes (128).",[20,75,77],{"id":76},"the-fp8-advantage-the-era-of-efficiency",[24,78,79],{},"The FP8 Advantage: The Era of Efficiency",[10,81,82],{},"The introduction of FP8 (8-bit floating point) precision has been a monumental step towards more efficient AI inference for the industry as a whole. By reducing the memory footprint and computational intensity, FP8 allows for larger models to be deployed or existing models to run at significantly higher throughputs while utilizing less memory. While FP8 support is available across modern AI hardware platforms from both AMD and NVIDIA, harnessing its full potential requires highly optimized software implementations.",[10,84,85],{},"We’ve been working tirelessly to integrate and optimize our kernels for FP8 on AMD. We’re incredibly proud to announce that our recent benchmarks demonstrate a clear victory for AMD MI300X equipped with Paiton’s optimized kernels.",[20,87,89],{"id":88},"paiton-on-amd-mi300x-setting-a-new-standard",[24,90,91],{},"Paiton on AMD MI300X: Setting a New Standard",[10,93,94],{},"Our internal testing shows that with Paiton’s optimized kernels, the AMD MI300X GPU achieves demonstrably better results compared to the NVIDIA H200 GPU when running the amd\u002FLlama-3.1-70B-Instruct-FP8-KV model for inference in FP8 precision.",[10,96,97],{},"Here are the benchmark results comparing NVIDIA H200 and AMD MI300X performance with Paiton’s optimized kernels:",[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],{},"Overall Winner",[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],{},"Draw",[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],{},"Note:"," In preliminary tests, Paiton’s FP8 kernels also outperformed AMD’s own Aiter engine on MI300X.",[10,476,477],{},[478,479],"img",{"alt":480,"src":481},"","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Fh200vsmi300xfp8.webp",[10,483,484,485,488],{},"The qualitative results are undeniable: ",[24,486,487],{},"Paiton enables the AMD MI300X to process Llama-3.1-70B-Instruct-FP8-KV queries with higher throughput and lower latency than its NVIDIA counterpart across small to mid-range batch sizes, and often achieves better Time to First Token (TTFT)."," This is a direct testament to the power of targeted kernel optimization. While NVIDIA H200 shows strong performance at the highest batch sizes, our focus on optimizing for the most common real-world scenarios (smaller, more frequent requests, typical of interactive AI applications) demonstrates Paiton’s significant and impactful advantage in practical deployments. This means faster responses for end-users and more efficient utilization of your AMD hardware in common operational profiles.",[20,490,492],{"id":491},"why-this-matters-for-you",[24,493,494],{},"Why This Matters for You",[34,496,497,503,514,524],{},[37,498,499,502],{},[24,500,501],{},"Unleash AMD’s True Potential:"," Investing in cutting-edge hardware like AMD MI300X GPUs should mean unlocking their full capabilities, not leaving performance on the table due to generic software. Paiton ensures you’re extracting every possible compute cycle, allowing your AMD infrastructure to reach its maximum potential for AI inference workloads. Our fine-tuned kernels mean your GPUs are working at peak efficiency, minimizing idle time and maximizing useful computation.",[37,504,505,508,509,513],{},[24,506,507],{},"Cost-Effective AI Deployment:"," Higher inference efficiency directly translates into tangible cost savings. When your models run faster and more efficiently, you can process more requests, or complete existing workloads in less time. This directly impacts your operational expenses, whether you’re managing an on-premise data center or utilizing cloud-based GPU instances. Over time, these optimizations can lead to ",[510,511,512],"em",{},"substantial reductions in your total cost of ownership"," for AI infrastructure.",[37,515,516,519,520,523],{},[24,517,518],{},"Future-Proof Your Deployments:"," The landscape of AI models is constantly evolving, with a clear trend towards larger, more complex architectures and the adoption of lower precision formats like FP8. As these models grow and their computational demands intensify, highly optimized inference solutions will become not just beneficial, but absolutely critical for maintaining performance and scalability. ",[510,521,522],{},"Paiton’s continuous development"," ensures your AI deployments remain at the forefront, ready to handle the next generation of models and precision requirements with confidence.",[37,525,526,529,530,533],{},[24,527,528],{},"Broader Hardware Choice:"," Our work with Paiton empowers developers and organizations to confidently choose AMD for their demanding AI inference needs. By demonstrating ",[510,531,532],{},"superior performance on AMD MI210, MI250X, MI300X, MI325X",", MI355X, we’re fostering a more competitive and innovative hardware ecosystem, giving you more flexibility and options in designing your AI infrastructure. This competition drives innovation across the industry, ultimately benefiting all users.",[10,535,536],{},"The era of one-size-fits-all AI optimization is rapidly drawing to a close. Paiton is at the forefront, leading the charge in delivering specialized, high-performance solutions meticulously crafted for AMD GPUs. With our latest enhancements, including the breakthrough FP8 optimizations, we’re not just optimizing; we’re actively redefining what’s possible for AI inference on AMD hardware.",[10,538,539],{},"Stay tuned for more in-depth technical breakdowns and further benchmark releases as we continue to push the boundaries of AI performance, and during these FP8 benchmarks we uncovered additional optimization techniques that we’ll showcase in upcoming deep-dive posts! We’ll soon be sharing exciting results on Tensor Parallelism (TP), where Paiton continues to demonstrate superior performance and scalability, even surpassing AMD’s own AITER engine in our internal tests. If you’re running AI models on AMD hardware, it’s time to experience the Paiton difference and see how our kernel optimizations can elevate your AI inference capabilities.",[10,541,542],{},"If you’re running AI models on AMD hardware, it’s time to experience the Paiton difference and see how our kernel optimizations can elevate your AI inference capabilities.",[10,544,545],{},"Reach out for a demo and elevate your AI inference performance today!",[10,547,548],{},[24,549,550,551],{},"– ",[510,552,553],{},"The Paiton Team –",{"title":480,"searchDepth":555,"depth":555,"links":556},2,[557,559,560,561],{"id":22,"depth":558,"text":26},3,{"id":76,"depth":558,"text":79},{"id":88,"depth":558,"text":91},{"id":491,"depth":558,"text":494},[563,564,183,565,566,567,568,569,570,571,572,573,574,575],"All","Artificial Intelligence","Uncategorized","AMD MI300X","Cold Start Optimization","Enterprise AI","Generative AI","GPU Performance","Inference Latency","Large Language Models","Llama 3.1 405B","Model Serving","vLLM Optimization","2025-06-08T19:12:40","Compare Paiton on AMD MI300X with NVIDIA H200 for Llama 3.1 70B FP8, including throughput, first-token delay and latency across batch sizes.","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":577},"paiton-fp8-beats-nvidias-h200-on-amds-mi300x","blog\u002Fpaiton-fp8-beats-nvidias-h200-on-amds-mi300x","aG3Hbyuu-w-C-MTcRIQRtg4uaZZor16Il9Rk4gwAXcU",[590,602,615,625,634,649,658,667,676,686,699,709,721,730,740,749,760,791,801,823,841,859,877,894,910,921,937,952,963,972,980,994,996,1007,1018,1028,1041,1051,1064,1075,1085,1096,1105,1117,1128,1137],{"path":591,"title":592,"description":593,"date":594,"slug":595,"image":596,"originalUrl":597,"categories":598},"\u002Fblog\u002Fpaiton-idol-radeon-ai-pro-r9700","The Radeon AI PRO R9700 does 3D too: Idol in 16.4 seconds","Idol turns an image into a 3D Gaussian splat in 16.44 seconds on one Radeon AI PRO R9700 with Paiton, versus 39.22 seconds for stock on the same GPU.","2026-11-06T09:00:00Z","paiton-idol-radeon-ai-pro-r9700","\u002Fasset\u002Fimages\u002Fblog\u002Fpaiton-idol\u002Fhero.webp","https:\u002F\u002Feliovp.com\u002Fblog\u002Fpaiton-idol-radeon-ai-pro-r9700",[183,599,600,601],"AMD Radeon","Local AI","3D Generation",{"path":603,"title":604,"description":605,"date":606,"slug":607,"image":608,"originalUrl":609,"categories":610},"\u002Fblog\u002Fpaiton-deepseek-v41-flash-amd-instinct-mi350p","Deepseek V4.1 Flash on a single MI350P","DeepSeek V4.1 Flash on one 144 GB MI350P: 77.9 tokens\u002Fs for one request and 1,107.6 in a 512-request batch, with Paiton and CPU expert offload.","2026-11-03T12:00:00Z","paiton-deepseek-v41-flash-amd-instinct-mi350p","\u002Fasset\u002Fimages\u002Fblog\u002Fpaiton-deepseek-v41\u002Fhero.webp","https:\u002F\u002Feliovp.com\u002Fblog\u002Fpaiton-deepseek-v41-flash-amd-instinct-mi350p",[183,611,612,613,614],"AMD Instinct","AI Inference","DeepSeek","Quantization",{"path":616,"title":617,"description":618,"date":619,"slug":620,"image":621,"originalUrl":622,"categories":623},"\u002Fblog\u002Fpaiton-qwen38-flash-next-amd-instinct-mi350p","Qwen3.8 Flash Next on MI350P: twice the speed | Paiton","Qwen3.8 Flash Next on one AMD MI350P: 2.24× the tested vLLM setup's single-request decode speed and about 2.2 million shared KV-cache tokens with Paiton.","2026-10-30T12:00:00Z","paiton-qwen38-flash-next-amd-instinct-mi350p","\u002Fasset\u002Fimages\u002Fblog\u002Fpaiton-mi350p\u002Fhero.webp","https:\u002F\u002Feliovp.com\u002Fblog\u002Fpaiton-qwen38-flash-next-amd-instinct-mi350p",[183,611,612,624,614],"Qwen",{"path":626,"title":627,"description":628,"date":629,"slug":630,"image":631,"originalUrl":632,"categories":633},"\u002Fblog\u002Fpaiton-qwen38-3bit-accuracy-prefix-caching-mtp","Qwen3.8 Flash Next: 3-bit near 16-bit accuracy, with MTP prefix caching","Paiton's new Qwen3.8 3-bit weights approach 16-bit task scores on two R9700 cards. Native MTP prefix caching resumes a 200K prompt in 0.68 seconds. Results, limits and setup.","2026-10-24T18:45:00Z","paiton-qwen38-3bit-accuracy-prefix-caching-mtp","\u002Fasset\u002Fimages\u002Fblog\u002Fpaiton-qwen38-3bit-mtp\u002Fhero.webp","https:\u002F\u002Feliovp.com\u002Fblog\u002Fpaiton-qwen38-3bit-accuracy-prefix-caching-mtp",[183,599,600,624,614],{"path":635,"title":636,"description":637,"date":638,"slug":639,"image":640,"originalUrl":641,"categories":642},"\u002Fblog\u002Fnvidia-dsx-pod-vera-rubin-modular-data-centers","Nvidia confirms the modular DC direction","NVIDIA DSX POD brings Vera Rubin AI factories to modular data centers. ElioVP explains site readiness, cooling and the thinking behind 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",[643,644,645,646,647,648],"Modular DC","AI Infrastructure","ModFlex","NVIDIA","Vera Rubin","Liquid Cooling",{"path":650,"title":651,"description":652,"date":653,"slug":654,"image":655,"originalUrl":656,"categories":657},"\u002Fblog\u002Fpaiton-qwen38-flash-next-4bit-radeon-ai-pro-r9700","Qwen3.8 Flash Next in 4-bit on 2 × Radeon R9700: tested against 16-bit","Paiton runs Qwen3.8 Flash Next in 4-bit on two R9700 cards: 96.8% GSM8K, 96.3% HumanEval, 189.8 tokens\u002Fs and an optional RAM prefix cache. Accuracy, speed and setup.","2026-10-12T15:00:00Z","paiton-qwen38-flash-next-4bit-radeon-ai-pro-r9700","\u002Fasset\u002Fimages\u002Fblog\u002Fpaiton-qwen38-flash-next-4bit\u002Fhero.webp","https:\u002F\u002Feliovp.com\u002Fblog\u002Fpaiton-qwen38-flash-next-4bit-radeon-ai-pro-r9700",[183,599,600,624,614],{"path":659,"title":660,"description":661,"date":662,"slug":663,"image":664,"originalUrl":665,"categories":666},"\u002Fblog\u002Fpaiton-qwen38-flash-next-radeon-ai-pro-r9700","Qwen3.8 Flash Next on 2 × Radeon AI PRO R9700: 216 tokens\u002Fs, 200K context","Paiton runs Qwen3.8 Flash Next with 3-bit experts on two R9700 cards: 216.3 tokens\u002Fs, 565.1 aggregate tokens\u002Fs and a separate 200K mode. Benchmarks, quality and setup.","2026-10-10T10:30:00Z","paiton-qwen38-flash-next-radeon-ai-pro-r9700","\u002Fasset\u002Fimages\u002Fblog\u002Fpaiton-qwen38-flash-next\u002Fhero.webp","https:\u002F\u002Feliovp.com\u002Fblog\u002Fpaiton-qwen38-flash-next-radeon-ai-pro-r9700",[183,599,600,624,614],{"path":668,"title":669,"description":670,"date":671,"slug":672,"image":673,"originalUrl":674,"categories":675},"\u002Fblog\u002Fpaiton-qwen38-w3a4-radeon-ai-pro-r9700","Qwen3.8 27B on 1 × Radeon AI PRO R9700: 3-bit weights, 20% faster decode","Qwen3.8 27B on one R9700: 19.9% faster weighted decode, a new 4-bit cache, 200K context and optional vision. Benchmarks and current Paiton setup.","2026-09-27T09:00:00Z","paiton-qwen38-w3a4-radeon-ai-pro-r9700","\u002Fasset\u002Fimages\u002Fblog\u002Fpaiton-qwen38-w3a4\u002Fhero.webp","https:\u002F\u002Feliovp.com\u002Fblog\u002Fpaiton-qwen38-w3a4-radeon-ai-pro-r9700",[183,599,600,624,614],{"path":677,"title":678,"description":679,"date":680,"slug":681,"image":682,"originalUrl":683,"categories":684},"\u002Fblog\u002Fpaiton-qwen-image-21-radeon-ai-pro-r9700","Qwen-Image 2.1 on 1 × Radeon AI PRO R9700: 2048×2048 images in 103 seconds","Generate 2048×2048 Qwen-Image 2.1 images locally with 1 × Radeon AI PRO R9700. The released Paiton v1.0.2 container measured 103.29 seconds per warm request, through PNG delivery.","2026-09-23T09:00:00Z","paiton-qwen-image-21-radeon-ai-pro-r9700","\u002Fasset\u002Fimages\u002Fblog\u002Fpaiton-qwen-image-21\u002Fhero.webp","https:\u002F\u002Feliovp.com\u002Fblog\u002Fpaiton-qwen-image-21-radeon-ai-pro-r9700",[183,599,600,685,624],"Image Generation",{"path":687,"title":688,"description":689,"date":690,"slug":691,"image":692,"originalUrl":693,"categories":694},"\u002Fblog\u002Fpaiton-qwen38-mxfp4-dflash2-r9700","Qwen3.8: 400.7 tok\u002Fs on R9700 | Paiton","Qwen3.8 on one R9700: 400.7 aggregate tok\u002Fs with ROCm 10 and vLLM 0.29, plus public 200K\u002F220K chat profiles. Benchmarks, limits and launch commands.","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",[183,599,695,696,697,698],"vLLM","Qwen3.8","Inference Optimization","DFlash2",{"path":700,"title":701,"description":702,"date":703,"slug":704,"image":705,"originalUrl":706,"categories":707},"\u002Fblog\u002Fpaiton-qwen38-neo-gguf-vllm-r9700","Qwen3.8 GGUF in vLLM: Faster Responses on One Radeon","Run the original NEO CODER MAX GGUF in vLLM with Paiton on an R9700. Explore measured latency gains, image input and local deployment.","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",[183,599,600,708,695],"GGUF",{"path":710,"title":711,"description":712,"date":713,"slug":714,"image":715,"originalUrl":716,"categories":717},"\u002Fblog\u002Fpaiton-minimax-h3-radeon-ai-pro-r9700","MiniMax H3 on Radeon: 15-Second Video With Native Sound","Paiton generates a 15-second MiniMax H3 video with stereo audio on one Radeon AI PRO R9700 in 5m 33s, with 16.7% lower latency than matched 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",[183,599,600,718,719,720],"Video Generation","MiniMax H3","ComfyUI",{"path":722,"title":723,"description":724,"date":725,"slug":726,"image":727,"originalUrl":722,"categories":728},"\u002Fblog\u002Fpaiton-flux2-klein-radeon-ai-pro-r9700","Local FLUX.2 klein on Radeon AI PRO R9700: Faster Image Generation with Less VRAM","Paiton generates 1024×1024 FLUX.2 klein images in 1.054 seconds on an R9700: 16.2% lower warm latency and 33.4% lower peak Torch allocation.","2026-09-07T09:00:00","paiton-flux2-klein-radeon-ai-pro-r9700","\u002Fasset\u002Fimages\u002Fblog\u002Fpaiton-flux2-klein\u002Ffox-paiton.webp",[183,599,600,685,729,720],"FLUX",{"path":731,"title":732,"description":733,"date":734,"slug":735,"image":736,"originalUrl":737,"categories":738},"\u002Fblog\u002Fpaiton-ornith15-radeon-ai-pro-r9700","Ornith 1.5 at 44.6 tok\u002Fs on One Radeon AI PRO R9700","Paiton serves Ornith 1.5 35B A3B at 44.63 output tok\u002Fs on one Radeon AI PRO R9700, 27% faster than tuned stock vLLM, with 21.3% lower modeled cost.","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",[183,564,599,612,570,571,697,572,695,739],"Cost Efficiency",{"path":741,"title":742,"description":743,"date":744,"slug":745,"image":746,"originalUrl":747,"categories":748},"\u002Fblog\u002Fpaiton-qwen38-radeon-ai-pro-r9700","Paiton: 21% More Qwen3.8 Throughput on Radeon AI PRO R9700","Paiton serves AMD’s Qwen3.8 27B at 39.77 output tokens\u002Fs on one Radeon AI PRO R9700, delivering 21% more throughput and 17.4% lower modeled cost.","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",[183,564,599,612,570,571,697,572,695,739],{"path":750,"title":751,"description":752,"date":753,"slug":754,"image":755,"originalUrl":579,"categories":756},"\u002Fblog\u002Fai-data-center-power-requirements-gpu-per-megawatt","AI Data Center Power Requirements: The GPU\u002FMW Illusion","Why do AI data-center proposals quote different GPU capacities? See how PUE, peak loads, storage, networking and cooling determine deployable compute.","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",[563,644,757,645,758,759],"Data Centers","HPC","AMD Helios",{"path":761,"title":762,"description":763,"date":764,"slug":765,"image":766,"originalUrl":767,"categories":768},"\u002Fblog\u002Fpaiton-returns-to-its-diffusion-roots-optimizing-wan2-2-t2v-a14b-on-amd-mi355x","Wan2.2 Video Generation: Paiton on AMD MI355X","Compare Wan2.2-T2V-A14B video generation on AMD MI355X with Paiton and NVIDIA B200 using Diffusers, and explore our diffusion optimization approach.","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",[563,564,183,769,770,771,772,773,774,775,776,569,777,778,779,780,781,782,783,784,183,785,786,787,788,789,790],"14B","AMD","B200","Benchmarks","Blackwell","Compute","Diffusion","Eliovp","GPU","Hardware","Inference","Instinct","MI355x","NVidia","On-Premise","Optimization","Sovereign AI","T2V","Text-to-Video","Tuning","Video-Generation","Wan2.2",{"path":792,"title":793,"description":794,"date":795,"slug":796,"image":797,"originalUrl":798,"categories":799},"\u002Fblog\u002Ffrom-the-attic-to-the-front-page-eliovp-recognized-as-a-pioneer-in-chip-optimization-data-center-infrastructure","ElioVP in De Tijd: Chip Optimization and Data Centers","Read about De Tijd's coverage of ElioVP, from its origins in chip optimization to its work on modular data centers and high-density cooling.","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",[563,564,643,565,770,800,643,782],"De Tijd",{"path":802,"title":803,"description":804,"date":805,"slug":806,"image":807,"originalUrl":808,"categories":809},"\u002Fblog\u002Fprivacy-is-geen-it-probleem-meer-het-is-een-strategische-prioriteit","AI Privacy: A Strategic Priority for Benelux Businesses","Explore generative AI privacy risks, trust, data retention and governance, and why Benelux businesses need a strategic approach to secure AI.","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",[563,564,810,565,811,812,813,814,815,816,817,818,776,819,569,820,821,822],"Trending","AI Act","Anthropomorphism","AVG","Benelux","ChatGPT","Cybersecurity","Data Governance","Data Security","GDPR","Microsoft Copilot","Privacy","Shadow AI",{"path":824,"title":825,"description":826,"date":827,"slug":828,"image":829,"originalUrl":830,"categories":831},"\u002Fblog\u002Fitsme-bij-ons-is-het-its-not-me-en-dit-is-waarom","Why We Do Not Use itsme: Privacy and Data Sovereignty","Why ElioVP does not use itsme: our assessment of identity metadata, cloud dependence, data sovereignty and authentication risks.","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",[563,832,833,834,816,835,836,837,819,838,839,840,821],"AWS","Belgian Mobile ID","Cloud Act","Data Sovereignty","Digital Identity","eIDAS","itsme","Liberty Global","MyGov.be",{"path":842,"title":843,"description":844,"date":845,"slug":846,"image":847,"originalUrl":848,"categories":849},"\u002Fblog\u002Ffield-report-the-reality-of-building-agentic-ai-in-2025","Field Report. The Reality of Building Agentic AI in 2025","Lessons from building on-premise AI agents in 2025 cover workflow design, observability, model training, hallucinations and GPU memory limits.","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",[563,564,850,810,851,852,853,854,568,855,856,857,785,858],"Solutions","Agentic AI","AI Engineering","AI Strategy","Autonomous Agents","Local LLM","Model Fine-Tuning","On-Premise AI","VRAM Optimization",{"path":860,"title":861,"description":862,"date":863,"slug":864,"image":865,"originalUrl":866,"categories":867},"\u002Fblog\u002Fthe-synthetic-unicorn-bubble","The Synthetic Unicorn Bubble","An analysis of AI neocloud investment risks, examining circular financing, infrastructure claims, contract terms and 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",[563,564,810,644,868,869,870,871,872,873,874,875,876],"AI Neocloud","Circular Financing","GPU Cloud","Investment Risks","Startup Valuation","Synthetic Bubble","Tech Analysis","Vaporware","Venture Capital",{"path":878,"title":879,"description":880,"date":881,"slug":882,"image":883,"originalUrl":884,"categories":885},"\u002Fblog\u002Fbuilding-the-engine-for-the-ai-race-the-4-month-path-to-nvidia-gb300-nvl72-power","NVIDIA GB300 NVL72: A Four-Month Modular Data Center Plan","Explore a modular data center design for NVIDIA GB300 NVL72, covering redundant power, hybrid cooling and a four-month deployment plan.","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",[563,643,565,886,644,887,888,648,889,890,891,892,893],"150kW Rack","DLC","High Density","Modular Data Center","NVIDIA Blackwell Ultra","NVIDIA GB300","NVL72","Rapid Deployment",{"path":895,"title":896,"description":897,"date":898,"slug":899,"image":900,"originalUrl":901,"categories":902},"\u002Fblog\u002Fwhy-cuda-translation-wont-unlock-amds-real-potential","Why “CUDA” Translation Won’t Unlock AMD’s Real Potential","Why CUDA compatibility is not the same as AMD performance: explore ROCm, HIP, kernel tuning and the case for hardware-specific optimization.","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",[563,564,183,565,566,564,903,904,905,906,907,908,183,909],"CUDA Translation","FP8","GPU Optimization","High Performance Computing","HIP","Kernel Tuning","ROCm",{"path":911,"title":912,"description":913,"date":914,"slug":915,"image":916,"originalUrl":917,"categories":918},"\u002Fblog\u002Fpaiton-the-simplest-way-to-supercharge-ai-inference","Paiton: The Simplest Way to Supercharge AI Inference","Learn how Paiton integrates with existing inference stacks, with AMD MI300X benchmark results and performance-per-dollar comparisons.","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",[563,564,183,612,611,566,739,919,697,908,183,920,695],"High Throughput","SGLang",{"path":922,"title":923,"description":924,"date":925,"slug":926,"image":927,"originalUrl":928,"categories":929},"\u002Fblog\u002Fstop-overpaying-paiton-mi300x-moe-beats-h200-b200-on-1m-tokens","Paiton MoE Benchmarks: MI300X vs H200 and B200","Compare Qwen3-30B-A3B MoE inference with Paiton on MI300X against H200 and B200, including throughput and cost per million 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",[563,564,183,930,566,931,697,932,933,934,935,183,936],"AI Benchmarks","Cost per Token","Mixture of Experts","MoE","NVIDIA B200","NVIDIA H200","Qwen3",{"path":938,"title":939,"description":940,"date":941,"slug":942,"image":943,"originalUrl":944,"categories":945},"\u002Fblog\u002Fagentic-ai-but-make-it-local-from-inbox-to-insight-to-action-en","Local Agentic AI: From Inbox to Action","Local-first AI agents turn email, documents and images into tickets, reports and actions, using models tailored to your data and systems.","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",[563,564,850,565,851,946,947,948,949,855,857,785,950,951],"Damage Detection","Document Processing","Email Automation","Invoice Extraction","Ticket Automation","Workflow Automation",{"path":953,"title":954,"description":955,"date":956,"slug":957,"image":958,"originalUrl":959,"categories":960},"\u002Fblog\u002Fmi300x-fp8-data-parallel-benchmarks-8-64-gpus-h200-left-behind-b200-within-reach","MI300X FP8 Benchmarks: GPU Partitioning with Paiton","Explore Llama 3.1 8B FP8 benchmarks on partitioned MI300X GPUs with Paiton, comparing throughput and latency against NVIDIA H200 and 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",[563,564,183,565,961,770,771,468,962,781,782,183,695],"AI","MI300X",{"path":964,"title":965,"description":966,"date":967,"slug":968,"image":969,"originalUrl":970,"categories":971},"\u002Fblog\u002Fapplicable-ai-for-businesses","Applicable AI for Businesses","Explore ElioVP's approach to local AI for business workflows, including custom model training and automated damage detection for logistics.","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",[563,564,850,851,946,947,948,949,855,857,785,950,951],{"path":973,"title":974,"description":975,"date":976,"slug":977,"image":480,"originalUrl":978,"categories":979},"\u002Fblog\u002Fintroducing-paitons-free-evaluation-models","Introducing Paiton’s Free Evaluation Models","Test Paiton with free evaluation models for AMD GPUs. Compare text, vision and image generation performance using your own workloads.","2025-07-07T11:26:13","introducing-paitons-free-evaluation-models","https:\u002F\u002Feliovp.com\u002Fintroducing-paitons-free-evaluation-models\u002F",[563,564,183],{"path":981,"title":982,"description":983,"date":984,"slug":985,"image":986,"originalUrl":987,"categories":988},"\u002Fblog\u002Fpaiton-dramatically-faster-startup-and-performance-for-llama-3-1-405b","Llama 3.1 405B: Faster Startup with Paiton on MI300X","See Paiton benchmarks for Llama 3.1 405B on eight AMD MI300X GPUs, covering model startup, tensor parallelism, throughput and 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",[563,564,183,565,612,566,989,904,990,573,991,183,992,993],"Cold Start","Graph Compilation","LLM Optimization","Startup Latency","Tensor Parallelism",{"path":584,"title":5,"description":577,"date":576,"slug":586,"image":580,"originalUrl":583,"categories":995},[563,564,183,565,566,567,568,569,570,571,572,573,574,575],{"path":997,"title":998,"description":999,"date":1000,"slug":1001,"image":1002,"originalUrl":1003,"categories":1004},"\u002Fblog\u002Fmi300x-vs-h200-vs-rx-7900-xtx-vs-tenstorrent-n300s-with-vllm","MI300X vs H200 vs RX 7900 XTX vs Tenstorrent n300s with vLLM","Compare MI300X, H200, RX 7900 XTX and Tenstorrent n300s on Llama 3 8B with vLLM, including throughput, modeled token costs and hardware limits.","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",[563,564,183,850,565,770,962,782,1005,1006],"RX7900XTX","tenstorrent",{"path":1008,"title":1009,"description":1010,"date":1011,"slug":1012,"image":1013,"originalUrl":1014,"categories":1015},"\u002Fblog\u002Fclusterpl-empowering-gpu-cluster-investors-with-real-world-financial-insights","ClusterP&L: Financial Modeling for GPU Clusters","Explore how ClusterP&L models GPU cluster costs, profitability and investment scenarios, with ROI metrics, risk simulations and exportable reports.","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",[563,564,643,850,771,468,1016,782,1017],"MI325x","pnl calculator",{"path":1019,"title":1020,"description":1021,"date":1022,"slug":1023,"image":1024,"originalUrl":1025,"categories":1026},"\u002Fblog\u002Fcranking-out-faster-tokens-for-fewer-dollars-amd-mi300x-vs-nvidia-h200","AMD MI300X vs. NVIDIA H200: Qwen3-32B with Paiton","Compare Qwen3-32B benchmarks on Paiton-optimized AMD MI300X and NVIDIA H200, covering throughput, latency and hardware costs.","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",[563,564,183,961,770,468,1027,782,183,695],"MI300",{"path":1029,"title":1030,"description":1031,"date":1032,"slug":1033,"image":1034,"originalUrl":1035,"categories":1036},"\u002Fblog\u002Fpower-meets-precision-high-density-modular-data-center-for-nvidia-nvl-deployments-1-2-mw","Modular Data Centers for NVIDIA NVL: 1 to 2 MW","Explore modular data center designs for NVIDIA NVL systems, covering power capacity, liquid cooling, redundancy and deployment planning.","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",[563,643,1037,644,888,758,648,889,1038,1039,892,1040],"1-2MW Data Center","NVIDIA Blackwell","NVIDIA NVL","Precision Cooling",{"path":1042,"title":1043,"description":1044,"date":1045,"slug":1046,"image":1047,"originalUrl":1048,"categories":1049},"\u002Fblog\u002Fexamining-ai-agents-in-the-medical-field-ai-that-speaks-dicom","Examining AI agents in the medical field: AI that speaks DICOM","Explore a local AI agent demo for DICOM workflows, from patient and study retrieval to a comparison of vision models using anonymized medical images.","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",[563,564,850,565,961,770,1050],"Healthcare",{"path":1052,"title":1053,"description":1054,"date":1055,"slug":1056,"image":1057,"originalUrl":1058,"categories":1059},"\u002Fblog\u002Feliovp-bv-your-trusted-partner-for-supply-chain-resilience-amidst-new-u-s-tariffs","U.S. Tariffs and AI Supply Chain Resilience: April 2025","Read ElioVP's April 2025 perspective on U.S. tariffs and supply chain resilience for AI servers, HPC systems and modular data centers.","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",[563,810,961,770,1060,1061,1062,1063],"import","Taiwan","Tariffs","Trump",{"path":1065,"title":1066,"description":1067,"date":1068,"slug":1069,"image":1070,"originalUrl":1071,"categories":1072},"\u002Fblog\u002Fwhy-ai-agents-are-the-future","Why AI Agents Are the Future","Explore AI agents for ERP, CRM, finance and customer support, with practical use cases and a path from workflow assessment to pilot and deployment.","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",[563,564,850,961,1073,1074],"AI Agents","ERP",{"path":1076,"title":1077,"description":1078,"date":1079,"slug":1080,"image":1081,"originalUrl":1082,"categories":1083},"\u002Fblog\u002Fthe-rise-of-open-source-ai-model-optimization","The Rise of Open-Source AI Model Optimization","Explore open-source AI optimization trends, from quantization and mixture-of-experts models to hardware-aware tuning, RAG and edge deployment.","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",[563,564,810,1084,770,777,782],"AI news",{"path":1086,"title":1087,"description":1088,"date":1089,"slug":1090,"image":1091,"originalUrl":1092,"categories":1093},"\u002Fblog\u002Fintroducing-our-benchmarking-tool-powered-by-dstack","Introducing Our Benchmarking Tool: Powered by dstack","Explore our dstack-powered tool for reproducible vLLM benchmarks, automated parameter sweeps and performance reports across local and cloud GPUs.","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",[563,564,183,961,770,1094,1095,962,183],"benchmark","LLM",{"path":1097,"title":1098,"description":1099,"date":1100,"slug":1101,"image":1102,"originalUrl":1103,"categories":1104},"\u002Fblog\u002Foptimizing-qwq-32b-by-qwen-amd-mi300x-vs-nvidia-h200","Optimizing QwQ-32B (by Qwen): AMD MI300X vs. NVIDIA H200","Compare QwQ-32B throughput and latency on AMD MI300X with Paiton and NVIDIA H200, from small batches to higher concurrency.","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",[563,564,183],{"path":1106,"title":1107,"description":1108,"date":1109,"slug":1110,"image":1111,"originalUrl":1112,"categories":1113},"\u002Fblog\u002Feliovp-featured-on-amd-tech-talk-podcast","Eliovp Featured on AMD “Tech Talk” Podcast","Listen to Elio Van Puyvelde and Jim Greene on AMD's Tech Talk podcast, discussing ElioVP's origins and its AI hardware and software services.","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",[563,770,1114,1115,1116],"Jim Greene","Podcast","Tech Talk",{"path":1118,"title":1119,"description":1120,"date":1121,"slug":1122,"image":1123,"originalUrl":1124,"categories":1125},"\u002Fblog\u002Ffurther-optimizing-amd-powered-inference-with-paiton","Further Optimizing AMD-Powered Inference with Paiton","Explore Paiton's DeepSeek R1 Distill Llama 8B benchmarks on AMD MI300X, focusing on throughput and first-token latency at smaller batch sizes.","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",[563,564,183,770,1126,1127,468,962,1016,183,695],"Deepseek","H100",{"path":1129,"title":1130,"description":1131,"date":1132,"slug":1133,"image":1134,"originalUrl":1135,"categories":1136},"\u002Fblog\u002Fa-first-look-at-paiton-in-action-deepseek-r1-distill-llama-3-1-8b","Paiton Benchmarks: DeepSeek R1 Distill Llama 3.1 8B","Compare stock and Paiton-optimized DeepSeek R1 Distill Llama 3.1 8B on AMD MI300X, with throughput and latency benchmarks across batch sizes.","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",[563,564,183,770,1126,1127,468,962,1016,183,695],{"path":1138,"title":1139,"description":1140,"date":1141,"slug":1142,"image":1143,"originalUrl":1144,"categories":1145},"\u002Fblog\u002Fai-model-optimization-with-paiton","AI Model Optimization with Paiton","Learn how Paiton uses model compilation, custom kernels and kernel fusion to optimize AI inference on AMD GPUs.","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",[563,564,183,770,1127,468,962,1016,183,695],1793962343010]