DeepSeek V4.1 Flash on Vera Rubin NVL72: 63-93x per-chip throughput vs GB300 in vLLM benchmarks
vllm_project · x · 2026-11-17
vLLM project published the first DeepSeek V4.1 Flash (552B, FP4) inference results on NVIDIA Vera Rubin NVL72, powered by Dynamo + vLLM on SemiAnalysis' AgentX benchmark. Compared to GB300 NVL72 with the same stack, InferenceX's perf ruler shows 63.4× total token throughput per chip at 400 tok/s/user and 93.3× at 600 tok/s/user.
More from Infra
- Why tensor parallelism breaks RNG reproducibility in model init — ezyang · 2026-11-17
- Bittensor's Engy tops Venice's AI inference volume despite 28x smaller valuation — markjeffrey · 2026-11-17
- Fractile raises $720M for AI inference chips, betting inference cost breaks AI economics first — YvesMulkers · 2026-11-17
- First DeepSeek V4.1 Flash results on Vera Rubin NVL72: up to 93.3x per-chip throughput vs GB300 — vllm_project · 2026-11-17
- Put an open-source AI on your phone in 10 minutes: free, offline, no account — alex_verem · 2026-11-17
- Cloudflare open-sources Kitesurf browser engine for agents, ships DO and spend-limit updates — ritakozlov · 2026-11-17