vLLM ships Day-0 support for Nemotron 3.5 Super VL in BF16 and NVFP4, 600+ tok/s on agentic tasks
vllm_project · x · 2026-10-15
vLLM announced Day-0 support for NVIDIA Nemotron 3.5 Super VL, offering both a BF16 baseline and an NVFP4 build with a smaller weight footprint and low-precision execution on NVIDIA Blackwell GPUs.
NVIDIA reports over 600 output tokens/sec at 100K input tokens on Artificial Analysis agentic tasks via a Baseten endpoint. A separate SWE-bench Pro comparison shows 4× faster task completion on 4× B200 GPUs with all models in NVFP4 and 50 TPS/user interactivity, charting the accuracy–completion-time tradeoff.
Related event: vLLM ships Day-0 support for Nemotron 3.5 Super VL(4 posts)→
More from Infra
- New inference engine 'e' hits 10,500 tok/s on a single DGX Station — brandon_galang · 2026-10-16
- SGLang ships Day-0 support for FLUX 3 Image Klein: 10 reference images, BF16/FP8/NVFP4 variants — ying11231 · 2026-10-16
- NVIDIA's Nemotron 3.5 Super VL hits CoreWeave: 12B-active multimodal MoE at $0.25/M input tokens — wandb · 2026-10-16
- Chip equipment beats bull case: 2026 WFE seen at $153B, $278B by 2030 — BenBajarin · 2026-10-16
- Steam now launches in 5.23s, beating Epic's 5.47s — and vLLM gets roasted for slow startup — AlpinDale · 2026-10-16
- Shadeform to Announce Six New Features on Oct 19: Lower GPU Costs, More Suppliers — _jaydeepkarale · 2026-10-16