Top all-time · #22926
CloudRift
Company blog · cloudrift.ai/blogaihardware
CloudRift is the company blog at cloudrift.ai, writing about ai and hardware. Since 2025, 3 different Hacker News readers have linked it 4 times. No feed was found, so read it on the site itself.
Too few sampled comments (1) to say how often HN recommends it.?
Why HN links it
Linked for a describing comment on an LLM inference throughput benchmark of RTX 4090, 5090 and PRO 6000 GPUs using vLLM serving and vLLM bench serve. The comment does not judge the writing.
Summarised by Claude from a sample of 1 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Sovereign AI platform for enterprise GPU infrastructure. Run LLM inference on-premise or in your security perimeter with full data sovereignty.
What Hacker News says?
I present an LLM inference throughput benchmark for RTX4090 / RTX5090 / PRO6000 GPUs based on vllm serving and vllm bench serve client benchmarking tool. The hardware configurations used: - 1x4090, 2x4090, 4x4090 - 1x5090; 2x5090; 4x5090 - 1x6000 All machines have at least 50GB of RAM per GPU with a minimum of 7 cores. The 4090 machines utilize the EPYC Milan (3rd Gen) processor, while the 5090/6000 models employ th…
Comment linking /blog/benchmarking-rtx-gpus-for-llm-inference
on a deleted threadSubmitted Building a GPU Compiler from Scratch as a story · 6 points
HN discussionSubmitted Limited-time GPU firepower Dirt-cheap LLM Inference: Llama 4, DeepSeek 0528 as a story · 3 points
HN discussionSubmitted Why Big Tech Turns Everything into a Knife Fight as a story · 1 points
HN discussion