A developer evaluated speculative decoding in vLLM on AMD Instinct MI300X and MI355X GPUs, testing draft methods including MTP, EAGLE-3, DFlash, and DSpark that propose candidate tokens verified in a …
AMD detailed its AMD Inference Microservices (AIMs), standardized Docker-based inference microservices that automatically select a runtime profile from inputs including model, precision, engine, laten…
AMD researchers introduced Zebra-HyLo, an upcycling recipe that converts pretrained Transformer models into long-context hybrid LLMs through post-training on roughly 10B tokens, without pretraining fr…
A developer published a step-by-step guide and open-source MCP toolkit for deploying Google's Gemma 4 E2B model to a single AMD Instinct MI300X GPU rented through AMD Developer Cloud at $1.99 per hour…
A developer built a suite of twelve tag-scoped MCP tools to inventory and manage a single AMD Instinct MI300X GPU on AMD Developer Cloud, using the same server to read the card's native numeric format…
A two-stage agentic pipeline combining GLM-4.7-Flash, a 30B tool-calling model, with Poro2, a 70-billion-parameter Finnish-language model, enriches medical terminology via Model Context Protocol tools…
AMD's experiments with speculative decoding in vLLM on AMD Instinct MI300X and MI355X GPUs using the ROCm platform show that output-token throughput gains vary by drafting method, proposal length, mod…
Signal65's new PINNACLE benchmark, developed with Kamiwaza, evaluates AI systems on whole enterprise task completion rather than model scores or token throughput, finding that 43 of 44 configurations …
VLLM's disaggregated serving using AMD's MORI-IO connector achieved 2.5x higher goodput on the same 8-GPU node compared to standard collocated serving, according to an April 2026 blog post. The benchm…
AMD has launched a multi-part study on memory instruction scheduling for lock-stepped kernels on its Instinct MI300X GPU, beginning with a tiled GEMM kernel example. The series aims to address bandwid…
AMD AI Workbench v2.0.0 now lets users onboard and deploy custom models from Hugging Face or private registries directly through its GUI, serving them as OpenAI-compatible endpoints via the same AMD I…
AMD introduced ROCm AMD Infinity Context (ROCm AIC), a purpose-built KV cache storage tier for distributed inference on AMD Instinct GPUs, starting with MI300X and MI350 Series. ROCm AIC uses low-late…
AMD Silo AI and the Autoware Foundation are using GPU partitioning on AMD Instinct MI300X accelerators to accelerate hyperparameter optimization for autonomous driving perception models, enabling up t…
AMD released AgentKernelArena, an open-source benchmarking framework for AI coding agents on GPU kernel optimization tasks using AMD Instinct GPUs. In tests on a 44-task subset, AMD's GEAKv3 agent ach…