News: 0001589087

  ARM Give a man a fire and he's warm for a day, but set fire to him and he's warm for the rest of his life (Terry Pratchett, Jingo)

Intel's LLM-Scaler Updated With OpenAI's GPT-OSS Model Support

([Intel] 6 Hours Ago llm-scaler-vllm)


Back in August was the announcement of [1]LLM-Scaler as part of Project Battlematrix . LLM-Scaler is a new Intel software project to provide optimized AI inference capabilities on Intel graphics hardware. A new beta release of LLM-Scaler "llm-scaler-vllm" is now available with expanded LLM model coverage.

Since the original August debut there have been more releases of this Docker-based LLM-Scaler solution for [2]delivering expanded model coverage and [3]other new features geared for Battlemage GPUs . Out today is a new llm-scaler-vllm release to once again expand the scope of supported large language models.

The new version today is llm-scaler-vllm beta release 0.10.2-b5. Significant with this updated Docker image is now supporting OpenAI's GPT-OSS models for inferencing with Intel Arc (Pro) B-Series GPUs. The GPT-OSS support should now be in good shape with this LLM-Scaler solution for Intel GPUs.

The updated LLM-Scaler also now enables the Qwen3-VL series and Qwen3-Omni series models too. That's all for the listed changes with today's beta release.

Those wanting to grab the new Intel LLM-Scaler-vLLM beta release can find the details on [4]GitHub .



[1] https://www.phoronix.com/news/Intel-LLM-Scaler-1.0

[2] https://www.phoronix.com/news/Intel-llm-scaler-vllm-Whisper

[3] https://www.phoronix.com/news/LLM-Scaler-Betas-EO-Q3

[4] https://github.com/intel/llm-scaler/releases/tag/vllm-0.10.2-b5



"Now I know why you say so little in person, you mouth is in a NOP because
the brain is always inserting requests at the top of the list_head."

- Andre Hedrick on Alan Cox