vLLM Achieves Day-0 Support for TML Inkling
vLLM Blog · rss · 2026-07-15
vLLM announced Day-0 support for Thinking Machines Lab's multimodal model, Inkling. By leveraging multi-token prediction (MTP), long-context serving, and parallel processing, vLLM optimized throughput to reach up to 380 tokens/s for a single user on NVIDIA GB200 GPUs.
More from Infra
- Why a 1GW Chinese AI data center may be plausible after all — teortaxesTex · 2026-07-22
- LFM2.5-8B-A1B doubles its tokenizer vocab and cuts on-device decoding time up to 3.7x — maximelabonne · 2026-07-22
- China’s AI arms race is increasingly defined by chips, data centers, and open models — BenBajarin · 2026-07-22
- Agent search bottlenecks are now about variance, not raw latency — rohanpaul_ai · 2026-07-22
- Gavin Baker argues Nvidia may be one of open source AI’s biggest supporters — GavinSBaker · 2026-07-22
- AI Power Demand Exposes US Energy Gap, Urging Shift from Scarcity to Abundance — bradneuberg · 2026-07-22