← Front page

The a16z Show · Thursday, August 6, 2026

VLLM's Broad Model Support and Hardware Vendor Collaboration

Simon Mo states that VLLM supports over a thousand model architectures, including many open-weight models, often seeing new models live on VLLM immediately upon release. He also mentions that VLLM works closely with hardware vendors like Nvidia, AMD, and Google, frequently serving as a benchmark for their newest chips.

personSimon MocompanyVLLMcompanyNvidiacompanyAMDcompanyGooglecompanyAmazon

The tape

3 quotes
So that means across like Nvidia, AMD, Google and Amazon, and a lot more, their newest chip will make sure VLM can run on them.
Simon Mo
And then in many cases they use VLM as a benchmark to make sure it runs well on them.
Simon Mo
Because for VLM, we support more than a thousand model architectures up to today, and a lot of those are proprietary, but also a lot of those are open weight.
Simon Mo
Heard on The a16z Show — “How Open-Source AI Became Critical Infrastructure, published Thursday, August 6, 2026. Heardvine summarizes and quotes with attribution and timestamps, and links to the original everywhere.
Transcribed via Gemini audio transcription · $0.05
VLLM's Broad Model Support and Hardware Vendor Collaboration — Heardvine