vLLM text image modality mismatch after GPU passthrough
Problem – Text‑Image Modality Mismatch after GPU Passthrough When running a multimodal model (e.g., llava‑1.5‑7b) inside a Docker container that uses the NVIDIA Container Toolkit, the generated responses contain text that is unrelated to the supplied image. The model appears to process the textual prompt correctly but ignores the visual content, resulting in incoherent or … Read more