From e18859298d109870b22cb5b8672d1078818e268d Mon Sep 17 00:00:00 2001 From: Michael Goin Date: Tue, 12 Aug 2025 20:14:46 -0400 Subject: [PATCH] Add hardware plugins to installation doc (#22732) Signed-off-by: Michael Goin Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com> Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com> --- docs/getting_started/installation/README.md | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/docs/getting_started/installation/README.md b/docs/getting_started/installation/README.md index a252343dcee8..f6ecceb85d86 100644 --- a/docs/getting_started/installation/README.md +++ b/docs/getting_started/installation/README.md @@ -14,3 +14,16 @@ vLLM supports the following hardware platforms: - [Google TPU](google_tpu.md) - [Intel Gaudi](intel_gaudi.md) - [AWS Neuron](aws_neuron.md) + +## Hardware Plugins + +The backends below live **outside** the main `vllm` repository and follow the +[Hardware-Pluggable RFC](../design/plugin_system.md). + +| Accelerator | PyPI / package | Repository | +|-------------|----------------|------------| +| Ascend NPU | `vllm-ascend` | | +| Intel Gaudi (HPU) | N/A, install from source | | +| MetaX MACA GPU | N/A, install from source | | +| Rebellions ATOM / REBEL NPU | `vllm-rbln` | | +| IBM Spyre AIU | `vllm-spyre` | |