# Native-speed vLLM transformers modeling backend

DevFeed: [Native-speed vLLM transformers modeling backend](<https://devfeed.tech/articles/native-speed-vllm-transformers-modeling-backend-7364.md>)

Original publisher: [Read original article](<https://huggingface.co/blog/native-speed-vllm-transformers-backend>)

Author: Harry Mellor; Lysandre

Published: 2026-07-08T00:00:00Z

Content type: article

Language: en

Sources: [Hugging Face - Blog](<https://devfeed.tech/sources/hugging-face-blog.md>)

Topics: [vllm](<https://devfeed.tech/topics/vllm.md>), [Inference Performance](<https://devfeed.tech/topics/inference-performance.md>), [Inference](<https://devfeed.tech/topics/inference.md>), [LLMs](<https://devfeed.tech/topics/llms.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>)

Tags: [architecture](<https://devfeed.tech/tags/architecture.md>), [batching](<https://devfeed.tech/tags/batching.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [inference](<https://devfeed.tech/tags/inference.md>), [inference-performance](<https://devfeed.tech/tags/inference-performance.md>), [llama](<https://devfeed.tech/tags/llama.md>), [llama-cpp](<https://devfeed.tech/tags/llama-cpp.md>), [llms](<https://devfeed.tech/tags/llms.md>), [mixture-of-experts](<https://devfeed.tech/tags/mixture-of-experts.md>), [mlx](<https://devfeed.tech/tags/mlx.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [sglang](<https://devfeed.tech/tags/sglang.md>), [transformers](<https://devfeed.tech/tags/transformers.md>), [vllm](<https://devfeed.tech/tags/vllm.md>)

## AI overview

This article describes the transformers modeling backend for vLLM and its role in serving Hugging Face models without requiring model authors to port their implementations. It explains how transformers supplies modeling code while vLLM contributes optimized inference techniques, and outlines comparisons with vLLM's native implementations across several Qwen3 model configurations. It also discusses inference-performance factors including GPU parallelization, compilation, fused kernels, and custom attention kernels.

## Source excerpt

We're on a journey to advance and democratize artificial intelligence through open source and open science.