InferenceX

(formerly InferenceMAX)

BySemiAnalysis logo
Star
DashboardMediaSupporters

InferenceX™ In the Media

Coverage and mentions of InferenceX™ (formerly InferenceMAX) across industry publications, blogs, and media outlets.

March 20, 2026
EE TimesArticle

“GTC 2026 Keynote: Long Live the Inference King”

March 20, 2026
Sina TechArticle

“英伟达热点小时报: 数据中心就是Token工厂 — Jensen Huang GTC 2026”

March 19, 2026
AMDVideo

“AMD Head of AI Product, Ramine Roane, shows his Inference King Champion Belt”

March 18, 2026
Morgan StanleyVideo

“Morgan Stanley TMT Conference 2026 (timestamp: 21:41)”

March 18, 2026
Spheron NetworkArticle

“NVIDIA H200 vs B200 vs GB200: Which GPU to Rent for AI in 2026?”

March 18, 2026
GMI Cloud (Juejin)Article

“GMI Cloud 成为英伟达 Dynamo 1.0 及 OpenShell 首发合作伙伴”

March 17, 2026
PYMNTSArticle

“Nvidia’s Jensen Huang Says AI Compute Could Near $1 Trillion by 2027”

March 17, 2026
Sebastian BarrosArticle

“Telcos are the best channel to Democratize AI”

March 16, 2026
NVIDIAVideo

“GTC 2026: Jensen announces that he is one of the Inference King”

March 16, 2026
NVIDIA Developer BlogArticle

“How NVIDIA Dynamo 1.0 Powers Multi-Node Inference at Production Scale”

March 10, 2026
TensorWaveArticle

“MI355X Just Flipped the Script on B200 for FP8 DeepSeek Disagg”

March 9, 2026
ForbesArticle

“Meta’s Most Efficient AI Infrastructure for Digital Intelligence”

March 7, 2026
The RegisterArticle

“Unpacking the deceptively simple science of tokenomics”

March 5, 2026
SAIL MediaVideo

“The Future of AI Infrastructure: Why Inference Max Matters”

March 4, 2026
GPU Mode By Mark Saroufim, Meta Pytorch EngineerVideo

“Lecture 100: InferenceX Continuous OSS Inference Benchmarking”

February 26, 2026
Chip BriefingArticle

“Weekly: Micron Leans Into Memory Supercycle”

February 24, 2026
SambaNovaArticle

“Introducing the SN50 RDU: Purpose-Built for Agentic Inference”

February 20, 2026
arXivArticle

“RPU -- A Reasoning Processing Unit”

February 19, 2026
SDxCentralArticle

“Nvidia pulls ahead as AMD’s software stack falls short: report”

February 17, 2026
AMD Developer BlogArticle

“Speed is the Moat: Inference Performance on AMD GPUs”

February 16, 2026
LMSys SGLangArticle

“SGLang is also officially crowned "InferenceMax King" by SemiAnalysis”

February 16, 2026
NVIDIA BlogArticle

“New SemiAnalysis InferenceX Data Shows NVIDIA Blackwell Ultra Delivers up to 50x Better Performance and 35x Lower Costs for Agentic AI”

February 16, 2026
SemiAnalysisArticle

“InferenceX v2: NVIDIA Blackwell Vs AMD vs Hopper”

February 16, 2026
WCCFTechArticle

“NVIDIA’s Blackwell Ultra Pushes "Agentic AI" Performance to New Heights, Delivering Up to 50× Higher Tokens/Watt & Stronger Long-Context Workloads”

February 6, 2026
Google Cloud BlogArticle

“Scaling MoE Inference with NVIDIA Dynamo on Google Cloud”

February 5, 2026
BasetenArticle

“How to run LLM performance benchmarks (and why you should)”

January 25, 2026
arXivArticle

“Kareus: Joint Reduction of Dynamic and Static Energy in Large Model Training”

January 5, 2026
NVIDIAVideo

“CES Analyst Q&A [timestamp - 3:37]”

November 19, 2025
NVIDIAArticle

“InferenceMAX Mention During NVIDIA Q3 FY2026 Report”

November 13, 2025
Red Hat - Co-Maintainers of vLLMVideo

“[vLLM Office Hours #37] InferenceMAX & vLLM”

November 11, 2025
AMD SVP of AI, Vamsi BoppanaVideo

“AMD Instinct MI350™: Generational Efficiency gains - Up to 10x on InferenceMAX”

October 28, 2025
NVIDIAVideo

“NVIDIA GTC DC 2025 - Jensen Huang talks about InferenceMAX”

October 24, 2025
Microsoft Azure Engineering BlogArticle

“Scaling Multi-Node LLM Inference with NVIDIA Dynamo and ND GB200 NVL72 GPUs on AKS”

October 16, 2025
CrusoeArticle

“The New AI Benchmark: Unlocking Real-World Performance with InferenceMAX by SemiAnalysis”

October 14, 2025
SGLang LMSYS OrgArticle

“SGLang and NVIDIA Accelerating SemiAnalysis InferenceMAX and GB200 Together”

October 13, 2025
NVIDIA Developer BlogArticle

“NVIDIA Blackwell Leads on SemiAnalysis InferenceMAX v1 Benchmarks”

October 10, 2025
TensorWaveArticle

“Benchmark Breakdown: How AMD’s MI300X, MI325X, and MI355X Are Redefining AI Inference Economics”

October 10, 2025
Tom's HardwareArticle

“InferenceMax AI Benchmark Tests Software Stacks, Efficiency, and TCO — Vendor-Neutral Suite Runs Nightly and Tracks Performance Changes Over Time”

October 9, 2025
SemiAnalysisArticle

“InferenceMAX™: Open Source Inference Benchmarking”

October 9, 2025
Barron’sArticle

“Nvidia, AMD Chips Compared in New Benchmarks. See Who Comes Out on Top.”

October 9, 2025
NVIDIA BlogArticle

“NVIDIA Blackwell Raises Bar in New InferenceMAX Benchmarks, Delivering Unmatched Performance and Efficiency”

October 9, 2025
vLLM BlogArticle

“SemiAnalysis InferenceMAX: vLLM and NVIDIA Accelerate Blackwell Inference”

October 9, 2025
AMD Developer BlogArticle

“InferenceMAX: Benchmarking Progress in Real Time”

October 9, 2025
Open Compute ProjectVideo

“SemiAnalysis InferenceMAX Benchmarking the AI Frontier”

October 9, 2025
NVIDIAVideo

“InferenceMAX Instagram Explainer”