{"slug": "triton-hf-builder-generate-nvidia-triton-repositories-from-hugging-face", "title": "Triton-hf-builder: Generate NVIDIA Triton repositories from Hugging Face checkpoints", "summary": "An open-source Python library and CLI called triton-hf-builder has been released to generate NVIDIA Triton model repositories from local Hugging Face checkpoints, producing model configuration, runtime adapters and dependency files for Transformers, vLLM and TensorRT-LLM. Repository generation runs without a GPU and does not load model weights, and the project ships a Docker quickstart that downloads a small checkpoint, starts CPU serving and sends an inference request. The tool is in beta, licensed under Apache-2.0, and installs via pip; model and hardware compatibility depends on the selected serving backend.", "body_md": "Hi everyone! I’m sharing **triton-hf-builder**, an open-source Python library and CLI that generates NVIDIA Triton model repositories from local Hugging Face checkpoints.\n\nIt creates model configuration, runtime adapters and dependency files for **Transformers, vLLM and TensorRT-LLM**. Repository generation runs without a GPU and does not load model weights.\n\nThe project includes a Docker quickstart that downloads a small checkpoint, starts CPU serving and sends an inference request.\n\n```\npip install triton-hf-builder\n```\n\nCurrently in beta, licensed under Apache-2.0. Model and hardware compatibility depends on the selected serving backend.\n\nFeedback, bug reports and experiences with different model architectures are welcome!", "url": "https://wpnews.pro/news/triton-hf-builder-generate-nvidia-triton-repositories-from-hugging-face", "canonical_source": "https://discuss.huggingface.co/t/triton-hf-builder-generate-nvidia-triton-repositories-from-hugging-face-checkpoints/191227#post_1", "published_at": "2026-10-30 10:50:44+00:00", "updated_at": "2026-10-30 11:17:36.702331+00:00", "lang": "en", "topics": ["ai-infrastructure", "ai-tools", "developer-tools", "large-language-models"], "entities": ["triton-hf-builder", "NVIDIA Triton", "Hugging Face", "Transformers", "vLLM", "TensorRT-LLM"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/triton-hf-builder-generate-nvidia-triton-repositories-from-hugging-face", "markdown": "https://wpnews.pro/news/triton-hf-builder-generate-nvidia-triton-repositories-from-hugging-face.md", "text": "https://wpnews.pro/news/triton-hf-builder-generate-nvidia-triton-repositories-from-hugging-face.txt", "jsonld": "https://wpnews.pro/news/triton-hf-builder-generate-nvidia-triton-repositories-from-hugging-face.jsonld"}}