From a921aa5859c69ba605dca0e382abaf297c4e64b9 Mon Sep 17 00:00:00 2001 From: Nicolas Mowen Date: Wed, 30 Oct 2024 06:26:48 -0600 Subject: [PATCH] Add specific information about GPUs that are supported for semantic search --- docs/docs/configuration/semantic_search.md | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) diff --git a/docs/docs/configuration/semantic_search.md b/docs/docs/configuration/semantic_search.md index 22c3ddfe9..01c8f9b79 100644 --- a/docs/docs/configuration/semantic_search.md +++ b/docs/docs/configuration/semantic_search.md @@ -54,10 +54,23 @@ semantic_search: ### GPU Acceleration -The CLIP models are downloaded in ONNX format, and the `large` model can be accelerated using GPU hardware, when available. This depends on the Docker build that is used, see [the object detector docs](../configuration/object_detectors.md) for more information. +The CLIP models are downloaded in ONNX format, and the `large` model can be accelerated using GPU hardware, when available. This depends on the Docker build that is used. + +:::info If the correct build is used for your GPU and the `large` model is configured, then the GPU will be automatically detected and used automatically. +**AMD** +- ROCm will automatically be detected and used for semantic search in the `-rocm` Frigate image. + +**Intel** +- OpenVINO will automatically be detected and used as a detector in the default Frigate image. + +**Nvidia** +- Nvidia GPUs will automatically be detected and used as a detector in the `-tensorrt` Frigate image. + +::: + ```yaml semantic_search: enabled: True