Intel Releases Updated LLM-Scaler-vLLM With Continuing To Expand Its LLM Support

Intel released llm-scaler-vllm beta 0.11.1-b7, adding symmetric 4-bit integer quantization for Qwen3 models, support for PaddleOCR and GLM-4.6v-Flash, and various bug fixes. The Docker-based solution helps deploy GenAI workloads on Intel Battlemage graphics cards, optimized for Arc Pro B60 but compatible with other Arc Graphics hardware with sufficient vRAM.