--- title: EAGLE-3 Speculative Decoding on AMD Instinct GPUs:... description: EAGLE-3 speculative decoding is now fully supported on AMD Instinct GPUs through a vLLM-centric pipeline built by the AMD Quark team. The workflow covers... canonical: https://daily.dev/posts/eagle-3-speculative-decoding-on-amd-instinct-gpus-training-and-serving-with-vllm-and-amd-quark-x5yf4izas twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: EAGLE-3 Speculative Decoding on AMD Instinct GPUs: Training and Serving with vLLM and AMD Quark | daily.dev og:description: EAGLE-3 speculative decoding is now fully supported on AMD Instinct GPUs through a vLLM-centric pipeline built by the AMD Quark team. The workflow covers... og:url: https://daily.dev/posts/eagle-3-speculative-decoding-on-amd-instinct-gpus-training-and-serving-with-vllm-and-amd-quark-x5yf4izas og:image: https://api.daily.dev/og/posts/X5yf4izas.png og:image:alt: EAGLE-3 Speculative Decoding on AMD Instinct GPUs: Training and Serving with vLLM and AMD Quark og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # EAGLE-3 Speculative Decoding on AMD Instinct GPUs: Training and Serving with vLLM and AMD Quark **[vLLM](https://daily.dev/sources/vllm)** · 12 min read · 0 upvotes · 0 comments ## Summary EAGLE-3 speculative decoding is now fully supported on AMD Instinct GPUs through a vLLM-centric pipeline built by the AMD Quark team. The workflow covers training EAGLE-3 draft models (using vLLM for on-policy data synthesis, hidden-state extraction, and in-loop evaluation), quantizing both target and draft models with AMD Quark MXFP4/FP8, and serving on ROCm/vLLM. Benchmarks on AMD Instinct MI355X show 1.69x–2.00x throughput gains for Kimi-K2.5 and up to 1.79x for MiniMax-M2.5 at 1K/1K workloads. The MiniMax-M3 EAGLE-3 draft trained in this pipeline achieves an average acceptance length of 2.77 across 11 domains on SPEED-Bench, remaining stable from 1K to 32K context. Day-0 MXFP4 checkpoints for major models are published on Hugging Face and run directly on ROCm/vLLM. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Exploring Speculative Decoding in vLLM on AMD GPUs](https://daily.dev/posts/exploring-speculative-decoding-in-vllm-on-amd-gpus-3xgpvjp6n) · vLLM · 1 upvotes · 0 comments - [Following the Bottleneck: Optimizing MiniMax M3 on AMD Instinct MI355X](https://daily.dev/posts/following-the-bottleneck-optimizing-minimax-m3-on-amd-instinct-mi355x-2n8wb31yk) · vLLM · 0 upvotes · 0 comments - [Speeding up LLM inference with P-EAGLE in vLLM Speculators](https://daily.dev/posts/speeding-up-llm-inference-with-p-eagle-in-vllm-speculators-zzmicyrfu) · Red Hat Developer · 2 upvotes · 0 comments - [Co-Designing AI Models Using Speculative Decoding for Faster LLM Inference](https://daily.dev/posts/co-designing-ai-models-using-speculative-decoding-for-faster-llm-inference-0zr9mkfau) · NVIDIA Developer · 0 upvotes · 0 comments --- Tags: [#ai-inference](https://daily.dev/tags/ai-inference), [#vllm](https://daily.dev/tags/vllm) [View this post on daily.dev](https://daily.dev/posts/eagle-3-speculative-decoding-on-amd-instinct-gpus-training-and-serving-with-vllm-and-amd-quark-x5yf4izas) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"EAGLE-3 Speculative Decoding on AMD Instinct GPUs: Training and Serving with vLLM and AMD Quark","url":"https://daily.dev/posts/eagle-3-speculative-decoding-on-amd-instinct-gpus-training-and-serving-with-vllm-and-amd-quark-x5yf4izas","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/eagle-3-speculative-decoding-on-amd-instinct-gpus-training-and-serving-with-vllm-and-amd-quark-x5yf4izas"},"datePublished":"2026-07-14T09:22:27.981Z","dateModified":"2026-07-14T12:02:13.565Z","description":"EAGLE-3 speculative decoding is now fully supported on AMD Instinct GPUs through a vLLM-centric pipeline built by the AMD Quark team. The workflow covers...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/6b6f9ba6b0883f46be43e21a4b27881c?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/6b6f9ba6b0883f46be43e21a4b27881c?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"vLLM","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"vLLM","logo":"https://media.daily.dev/image/upload/s--hTxEuls9--/f_auto/v1744613054/logos/vllm","url":"https://daily.dev/sources/vllm"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/eagle-3-speculative-decoding-on-amd-instinct-gpus-training-and-serving-with-vllm-and-amd-quark-x5yf4izas","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-inference,vllm","timeRequired":"PT12M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"vLLM","item":"https://daily.dev/sources/vllm"},{"@type":"ListItem","position":3,"name":"EAGLE-3 Speculative Decoding on AMD Instinct GPUs: Training and Serving with vLLM and AMD Quark"}]} ```