Infomaniak Fixes TranslateGemma 4B to Run on Standard Production Servers Infomaniak's AI team published a vLLM-compatible checkpoint of Google's TranslateGemma 4B that moves language metadata into ordinary message text, letting the translation model run on vLLM and SGLang production inference servers without wrapping the Transformers pipeline. The build replaces the custom source_lang_code and target_lang_code fields with a delimiter format (<<>>...<<>>...<<>>...), flattens the upstream RoPE configuration into one linear-scaling block, and changes the end-of-sequence token from to so generation terminates correctly. Infomaniak retained the original weights, which cover 55 languages, accept text or 896x896 images for OCR-plus-translate in one call, and score MetricX 5.32 and COMET 81.6 on WMT24++; the model was fine-tuned from Gemma 3 with 4.3B SFT tokens plus 10.2M RL tokens under the Gemma license. Infomaniak Fixes TranslateGemma 4B to Run on Standard Production Servers Infomaniak repackaged Google's TranslateGemma 4B so it runs cleanly on vLLM and SGLang, adding a delimiter-based language code format for serving. - Infomaniak released a vLLM-compatible build https://huggingface.co/Infomaniak-AI/vllm-translategemma-4b-it?utm source=alphasignal of Google's TranslateGemma 4B translation model. - Custom language-code fields are replaced by a delimiter format: <<