{"type":"post","id":"vllm-adds-day-0-support-for-nvidia-vera-aaa9ff","slug":"vllm-adds-day-0-support-for-nvidia-vera-aaa9ff","title":"vLLM adds day-0 support for NVIDIA Vera Rubin NVL72 via nightly cu134 containers.","description":"**Thesis:** Runtime readiness for a new accelerator can arrive before broad production evidence, because compatibility and tuned execution paths are established in layers.","retrieval_nugget":"**Thesis:** Runtime readiness for a new accelerator can arrive before broad production evidence, because compatibility and tuned execution paths are established in layers.","published_at":"2026-10-10","updated_at":"2026-10-10","record_date":"2026-10-10","date_kind":"published_at","topics":[],"source_urls":["https://vllm.ai/blog/2026-10-09-vera-rubin-preview"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:vllm-adds-day-0-support-for-nvidia-vera-aaa9ff","status":"published","visuals":[],"editorial_provenance":{"schema_version":"newruntime-editorial-copy-v1","content_status":"source_grounded_final","final_copy_sha256":"sha256:ea40ddd225e3162215c66a3b2c5f1783826defdf7103aee2a1cb260058478dfa","reviewed_at":"2026-10-10T08:42:10.678Z","source_evidence_count":1,"verified_claim_count":4,"site_analysis_schema_version":"newruntime-site-analysis-v1","site_object_kind":"field_note","observed_fact_count":4,"implication_count":1,"watch_condition_count":1,"related_record_count":0},"analysis":{"schema_version":"newruntime-site-analysis-v1","object_kind":"field_note","thesis":"Runtime readiness for a new accelerator can arrive before broad production evidence, because compatibility and tuned execution paths are established in layers.","observed_facts":[{"text":"vLLM says it runs on Vera Rubin NVL72 today and provides daily container builds.","source_urls":["https://vllm.ai/blog/2026-10-09-vera-rubin-preview"]},{"text":"The post names DeepSeek, Moonshot AI, Z.ai, and MiniMax among supported models.","source_urls":["https://vllm.ai/blog/2026-10-09-vera-rubin-preview"]},{"text":"It says Blackwell kernels are compatible with Rubin and identifies Rubin-tuned attention, GEMM, and MoE kernels through FlashInfer 0.7.0.","source_urls":["https://vllm.ai/blog/2026-10-09-vera-rubin-preview"]},{"text":"The post reports 7.8× per-GPU throughput versus GB200 NVL72 on AgentX at matched interactivity.","source_urls":["https://vllm.ai/blog/2026-10-09-vera-rubin-preview"]}],"mechanism":"The initial path reuses a compatible kernel family, while hardware-specific kernels and locality-aware weight placement target bottlenecks exposed by Rubin.","why_now":"vLLM’s preview presents day-0 support as available now through daily builds, making the announcement a deployment signal rather than only a future roadmap item.","implications":["Builders evaluating Rubin can begin testing workloads and deployment paths on the runtime, but should treat benchmark claims as workload-specific rather than a forecast of their own results."],"evidence_boundary":"The source is a project preview with early results; it does not establish independent reproduction, production-wide availability, or comparable gains across workloads.","watch_conditions":["Whether later releases document stable support, reproducible benchmarks across workloads, and the operational requirements for locality-domain enablement."],"related_records":[],"new_branch_reason":"The distinction between compatibility and tuning is the useful analytical record here: it separates an initial software bring-up milestone from evidence that the hardware yields repeatable serving gains. No prior New Runtime record was supplied for this branch."},"editor":{"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"routes":{"html":"https://newruntime.com/posts/vllm-adds-day-0-support-for-nvidia-vera-aaa9ff/","markdown":"https://newruntime.com/posts/vllm-adds-day-0-support-for-nvidia-vera-aaa9ff.md","json":"https://newruntime.com/posts/vllm-adds-day-0-support-for-nvidia-vera-aaa9ff.json"},"next_reads":[{"type":"collection","path":"/posts/","url":"https://newruntime.com/posts/","title":"Field Notes","reason":"Open the latest editorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/posts.json"},{"type":"collection","path":"/source-ledger.json","url":"https://newruntime.com/source-ledger.json","title":"Source Ledger","reason":"Inspect the public source evidence graph.","media_type":"application/json"}]}