NuMind

NuMind open-sources a vLLM extension that returns a served LLM's last hidden state as an embedding

GitHub numindai/vLLM-Last-Hidden-State published this on Oct 12, 2026 (source: github.com).

NuMind's Apache-2.0 vLLM-Last-Hidden-State extension lets a one-token chat request return the hidden-state vector behind the first generated token, so a model already served by vLLM can produce text and image representations without a second forward pass or a separate embedding server. Normal chat and streaming keep working on the same server, and the vector comes back through the OpenAI client. NuMind, which makes the NuExtract3 model, has opened upstream vLLM PR #57185 to merge it, and notes embedding quality depends on the model and prompt.