Articles

Insights on AI inference benchmarking, GPU performance, and ML infrastructure.

All announcement benchmark gpu inference

February 16, 2026·45 min read

InferenceX v2: NVIDIA Blackwell Vs AMD vs Hopper - Formerly InferenceMAX

GB300 NVL72, MI355X, B200, H100, Disaggregated Serving, Wide Expert Parallelism, Large Mixture of Experts, SGLang, vLLM, TRTLLM

benchmarkgpuinferenceannouncement

October 9, 2025·37 min read

InferenceMAX: Open Source Inference Benchmarking

NVIDIA GB200 NVL72, AMD MI355X, Throughput Token per GPU, Latency Tok/s/user, Perf per Dollar, Cost per Million Tokens, Tokens per Provisioned Megawatt, DeepSeek R1 670B, GPTOSS 120B, Llama3 70B

benchmarkgpuinferenceannouncement