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

[1/N] Initial prototype for multi-modal processor (#10044)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2024-11-13 20:39:03 +08:00
committed by GitHub
parent bb7991aa29
commit 0b8bb86bf1
48 changed files with 1132 additions and 436 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/source/models/enabling_multimodal_inputs.rst
View File

@@ -66,7 +66,7 @@ A default mapper is available for each modality in the core vLLM library. This i
3. Register maximum number of multi-modal tokens
------------------------------------------------
For each modality type that the model accepts as input, calculate the maximum possible number of tokens per data instance
For each modality type that the model accepts as input, calculate the maximum possible number of tokens per data item
and register it via :meth:`INPUT_REGISTRY.register_dummy_data <vllm.inputs.registry.InputRegistry.register_max_multimodal_tokens>`.
.. code-block:: diff