biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Frontend] Refactor prompt processing (#4028)

Browse Source 
Co-authored-by: Roger Wang <ywang@roblox.com>
This commit is contained in:
Cyrus Leung
2024-07-23 01:13:53 +08:00
committed by GitHub
parent 89c1c6a196
commit 739b61a348
24 changed files with 699 additions and 391 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/source/dev/multimodal/multimodal_index.rst
View File

@@ -8,7 +8,7 @@ Multi-Modality
vLLM provides experimental support for multi-modal models through the :mod:`vllm.multimodal` package.
Multi-modal inputs can be passed alongside text and token prompts to :ref:`supported models <supported_vlms>`
via the ``multi_modal_data`` field in :class:`vllm.inputs.PromptStrictInputs`.
via the ``multi_modal_data`` field in :class:`vllm.inputs.PromptInputs`.
Currently, vLLM only has built-in support for image data. You can extend vLLM to process additional modalities
by following :ref:`this guide <adding_multimodal_plugin>`.

2
docs/source/dev/offline_inference/llm_inputs.rst
View File

@@ -1,7 +1,7 @@
LLM Inputs
==========
.. autodata:: vllm.inputs.PromptStrictInputs
.. autodata:: vllm.inputs.PromptInputs
.. autoclass:: vllm.inputs.TextPrompt
:show-inheritance: