MLPerf Inference 6.1 landed yesterday and the AMD number I care about is software, not a…
This is a AI post classified by Jev as AI infra & evals (a model release), kept by the AI Radar because it carries real work, not commentary.
MLPerf Inference 6.1 landed yesterday and the AMD number I care about is software, not a new chip. Same MI355X: GPT-OSS-120B Server up 38%, Offline 28%, Wan 2.2 single-stream up 70% vs the last round. Crusoe ran 512 GPUs. That’s the public audit trail for the six-week ROCm cadence. https://mlcommons.org/2026/09/mlperf-inference-v6-1-results/
Posted by Mike Gannotti (53k followers) 2 days ago · 2 likes · 524 views · view the original post on X. Kept by the AI Radar as AI infra & evals.
More AI work like this
- Trains your own large language model from scratch using plain PyTorch. — @tom_doerr
- Here's a useful use-case for @typesafeai for a change. — @iam_zachi
- This is genius. — @daniel_mac8
- Which GPU should you use for embedding workloads? — @runpod
- Big update to the @Alibaba_Qwen Qwen3.8-Flash-Next single DGX Spark recipe! — @jvr0x
- 🔰 The Databricks Advanced Learning Festival runs September 16 through October 14, with… — @databricks
- Q: What is a trace? — @HamelHusain
- Inference scaling part 1. — @rasbt
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 27.2k posts from 4.8k X accounts over the last 14 days, 1.2k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 18:45 UTC. Full method.