{"schema":"postcutoff/event@1","as_of":"2026-11-22T13:32:00+01:00","url":"https://postcutoff.com/e/2026-09-16-mlperf-inference-v6-1/","md":"https://postcutoff.com/e/2026-09-16-mlperf-inference-v6-1/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"2026-09-16-mlperf-inference-v6-1","date":"2026-09-16","date_precision":"day","short_title":"MLPerf Inference v6.1 draws a record 30 submitters and the first Vera Rubin NVL72 results","deck":null,"takeaway":null,"category":"benchmark","category_label":"Benchmarks","importance":3,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":[{"n":1,"title":"MLCommons: Participation record with new MLPerf Inference v6.1 results","url":"https://mlcommons.org/2026/09/mlperf-inference-v6-1-results/","type":"official","group":"primary","domain":"mlcommons.org"},{"n":2,"title":"MLCommons: Where the industry is investing — a look at MLPerf Inference v6.1","url":"https://mlcommons.org/2026/09/chairs-mlperf-inference-v6-1/","type":"official","group":"primary","domain":"mlcommons.org"},{"n":3,"title":"NVIDIA: Vera Rubin NVL72 delivers leading performance in MLPerf Inference v6.1 debut","url":"https://blogs.nvidia.com/blog/vera-rubin-nvl72-mlperf-inference/","type":"official","group":"primary","domain":"blogs.nvidia.com"},{"n":4,"title":"Nebius: MLPerf Inference v6.1 results on Vera Rubin NVL72","url":"https://nebius.com/blog/posts/mlperf-inference-v6-1-results","type":"official","group":"primary","domain":"nebius.com"},{"n":5,"title":"AMD ROCm blog: MLPerf Inference v6.1 submission","url":"https://rocm.blogs.amd.com/artificial-intelligence/mlperf-inf-v6.1/README.html","type":"official","group":"primary","domain":"rocm.blogs.amd.com"},{"n":6,"title":"GlobeNewswire: MLCommons press release (Sept 16, 2026)","url":"https://www.globenewswire.com/news-release/2026/09/16/3363348/0/en/mlcommons-sets-participation-record-with-new-mlperf-inference-v6-1-benchmark-results.html","type":"press","group":"press","domain":"globenewswire.com"},{"n":7,"title":"TechTimes: MLPerf v6.1 puts first peer-reviewed numbers on Vera Rubin","url":"https://www.techtimes.com/articles/327658/20260917/mlperf-v61-puts-first-peer-reviewed-numbers-vera-rubin-software-gains-beat-new-hardware.htm","type":"press","group":"press","domain":"techtimes.com"}],"official":5,"filed":"2026-10-02","updated":"2026-10-02","orgs":["MLCommons","NVIDIA"],"title":"MLPerf Inference v6.1: record 30 submitters, first peer-reviewed Vera Rubin NVL72 results, new RAG and edge-agentic tests","summary":"On Sept 16, 2026 MLCommons published MLPerf Inference v6.1 results with a record 30 submitting organizations, two new tests (End-to-End RAG and Edge Agentic Inference) and the first peer-reviewed numbers for NVIDIA's Vera Rubin NVL72 (preview), which NVIDIA says delivers up to 3.7x the throughput of GB300 NVL72 on Qwen3-VL and up to 2.5x on DeepSeek-R1. MLCommons also said the new MLPerf Endpoints suite will replace Inference for the datacenter.","key_facts":["Record 30 submitting organizations, six first-time submitters (Atlas Inference, Crusoe, Orrick, ScitiX, VibeHPC, Naeem Khoshnevis)","New tests: End-to-End RAG (embedding → retriever → re-ranker → LLMs) and Edge Agentic Inference (multi-turn agentic workloads at the edge; NVIDIA ran it with Qwen3.6-27B on Jetson AGX Thor)","Speculative decoding now allowed in the interactive scenario for two benchmarks, plus GPT-OSS","Five new processors/accelerators: AMD Ryzen AI Max+ 395, AMD Instinct MI350P, Intel Arc Pro B70 (available); NVIDIA Rubin and Vera Rubin NVL72 (preview)","Largest system ever submitted to MLPerf Inference: 512 accelerators; plus a heterogeneous two-vendor system and one geographically distributed across the Pacific Ocean","Best per-accelerator server result: VLM test up 2.99x vs v6.0 (six months earlier); DeepSeek-R1 test up 5.7x vs v5.1 (one year earlier)","NVIDIA: Vera Rubin NVL72 up to 3.7x GB300 NVL72 throughput on Qwen3-VL (vLLM + Dynamo) and up to 2.5x on DeepSeek-R1 (TensorRT-LLM); DeepSeek-R1 scaled from 1 to 4 GB300 NVL72 racks (288 GPUs) at 99% scaling efficiency","Over 50% of submitters used MLPerf's new API-centric harness; MLCommons says MLPerf Endpoints 'will replace Inference in our family of benchmarks for the datacenter'"],"key_numbers":[],"tags":["mlperf","inference","benchmark","vera-rubin","nvidia","amd","intel","hardware","agentic","rag"],"science":null,"body_md":"## What happened\n\nMLCommons released MLPerf Inference v6.1 on Sept 16, 2026. The round set a participation record (30 organizations) and added two tests aimed at multi-step deployments: an End-to-End RAG pipeline and an Edge Agentic Inference test for\nmulti-turn agentic workloads on single-user edge devices. Speculative decoding became an allowed optimization in some interactive scenarios.\n\nNVIDIA submitted preview results for Vera Rubin NVL72 on DeepSeek-R1 and Qwen3-VL, the platform's first peer-reviewed benchmark numbers,\nclaiming up to 3.7x (Qwen3-VL) and 2.5x (DeepSeek-R1) the throughput of GB300 NVL72. Nebius also submitted Vera Rubin NVL72 preview results.\nAMD (Instinct MI350P, Ryzen AI Max+ 395) and Intel (Arc Pro B70) debuted new chips. NVIDIA additionally cited a 30x gain over GB300 NVL72\nin SemiAnalysis's AgentX benchmark in preview testing (not an MLPerf result).\n\nMLCommons said its new API-centric harness, used by over half of submitters, is the basis of \"MLPerf Endpoints\", which will replace\nMLPerf Inference for datacenter systems.\n\n## Why it matters\n\nMLPerf is the main audited cross-vendor inference benchmark. This round gave the first independent check on Vera Rubin's claimed\ngenerational gains, and its new tests show the benchmark following the industry from single-shot chat toward RAG pipelines and agents.","disputed":[],"related":[{"id":"2026-08-26-nvidia-q2-fy2027-vera-rubin-production","url":"https://postcutoff.com/e/2026-08-26-nvidia-q2-fy2027-vera-rubin-production/","date":"2026-08-26","date_precision":"day","short_title":"NVIDIA posts $96.2B quarter","deck":"Vera Rubin in full production and deploying at major clouds","takeaway":"Vera Rubin shipping in volume in H2 2026 is the compute step-change that 2027 frontier models will be trained and served on; NVIDIA's near-$100B quarter is the clearest financial measure of the AI buildout's scale.","category":"hardware-compute","category_label":"Chips & compute","importance":4,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":2,"official":1,"filed":"2026-09-29","updated":"2026-09-29","orgs":["NVIDIA"]},{"id":"2026-03-16-nvidia-gtc-2026-vera-rubin-feynman","url":"https://postcutoff.com/e/2026-03-16-nvidia-gtc-2026-vera-rubin-feynman/","date":"2026-03-16","date_precision":"day","short_title":"NVIDIA GTC 2026: Vera Rubin platform, Groq 3 LPX, Feynman preview and $1T demand outlook","deck":null,"takeaway":"It set the hardware roadmap that most frontier labs' 2026-2028 compute plans depend on, and signaled NVIDIA's push into inference-specialized silicon and agent software.","category":"hardware-compute","category_label":"Chips & compute","importance":4,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":5,"official":2,"filed":"2026-09-29","updated":"2026-09-29","orgs":["NVIDIA"]}],"people":[],"posts":[],"videos":[],"models":[],"changes":[{"date":"2026-10-02","type":"filed","text":"Created (found via NVIDIA blog while checking lab news)."}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-10-02","run":null,"sources_read":null,"updated":"2026-10-02","human_review":null,"version":{"date":"2026-10-07"}},"gaps":[{"model_id":"gpt-6-2-astra","name":"GPT-6.2 Astra","cutoff":"2026-05","days_after":108,"in_training_data":false},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":78,"in_training_data":false},{"model_id":"gemini-4-hydrogen","name":"Gemini 4 Hydrogen","cutoff":"2026-03","days_after":169,"in_training_data":false},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":108,"in_training_data":false}],"short_url":null}