From 11fbad191153b6a9ae5cd9a2574e120f108586b9 Mon Sep 17 00:00:00 2001 From: DarkLight1337 Date: Mon, 2 Dec 2024 17:02:22 +0000 Subject: [PATCH] Place them under Models for now Signed-off-by: DarkLight1337 --- docs/source/index.rst | 4 ++-- docs/source/{usage => models}/generative_models.rst | 4 ++-- docs/source/{usage => models}/pooling_models.rst | 4 ++-- 3 files changed, 6 insertions(+), 6 deletions(-) rename docs/source/{usage => models}/generative_models.rst (99%) rename docs/source/{usage => models}/pooling_models.rst (99%) diff --git a/docs/source/index.rst b/docs/source/index.rst index ba8442ba046cd..f64dd7fc4cc3b 100644 --- a/docs/source/index.rst +++ b/docs/source/index.rst @@ -93,6 +93,8 @@ Documentation :caption: Models models/supported_models + models/generative_models + models/pooling_models models/adding_model models/enabling_multimodal_inputs @@ -100,8 +102,6 @@ Documentation :maxdepth: 1 :caption: Usage - usage/generative_models - usage/pooling_models usage/lora usage/multimodal_inputs usage/structured_outputs diff --git a/docs/source/usage/generative_models.rst b/docs/source/models/generative_models.rst similarity index 99% rename from docs/source/usage/generative_models.rst rename to docs/source/models/generative_models.rst index 8f08b60751cba..253b7f60a7af5 100644 --- a/docs/source/usage/generative_models.rst +++ b/docs/source/models/generative_models.rst @@ -1,7 +1,7 @@ .. _generative_models: -Using Generative Models -======================= +Generative Models +================= vLLM provides first-class support for generative models, which covers most of LLMs. diff --git a/docs/source/usage/pooling_models.rst b/docs/source/models/pooling_models.rst similarity index 99% rename from docs/source/usage/pooling_models.rst rename to docs/source/models/pooling_models.rst index 7cbee67c66d4d..5d9b62a832e87 100644 --- a/docs/source/usage/pooling_models.rst +++ b/docs/source/models/pooling_models.rst @@ -1,7 +1,7 @@ .. _pooling_models: -Using Pooling Models -==================== +Pooling Models +============== vLLM also supports pooling models, including embedding, reranking and reward models.