A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 16, 15:45 UTC
[Doc] Update doc for Transformers 4.45 (#8817)
Roger Wang committed
Sep 25, 2024 at 13:29 UTC
e2c6e0a8291126c868b669f631837c7781646fdc
1 file changed
+3
-3
docs/source/models/supported_models.rst
+3
-3
@@ -242,12 +242,12 @@ Multimodal Language Models
242
* - :code:`LlavaNextVideoForConditionalGeneration`
243
- LLaVA-NeXT-Video
244
- Video
245
- - :code:`llava-hf/LLaVA-NeXT-Video-7B-hf`, etc. (see note)
245
+ - :code:`llava-hf/LLaVA-NeXT-Video-7B-hf`, etc.
246
-
247
* - :code:`LlavaOnevisionForConditionalGeneration`
248
- LLaVA-Onevision
249
- Image\ :sup:`+` / Video
250
- - :code:`llava-hf/llava-onevision-qwen2-7b-ov-hf`, :code:`llava-hf/llava-onevision-qwen2-0.5b-ov-hf`, etc. (see note)
250
+ - :code:`llava-hf/llava-onevision-qwen2-7b-ov-hf`, :code:`llava-hf/llava-onevision-qwen2-0.5b-ov-hf`, etc.
251
-
252
* - :code:`MiniCPMV`
253
- MiniCPM-V
@@ -298,7 +298,7 @@ Multimodal Language Models
298
For more details, please see: https://github.com/vllm-project/vllm/pull/4087#issuecomment-2250397630
299
300
.. note::
301
- For :code:`LLaVA-NeXT-Video`, :code:`LLaVA-Onevision` and :code:`Qwen2-VL`, the latest release of :code:`huggingface/transformers` doesn't work yet, so we need to use a developer version (:code:`21fac7abba2a37fae86106f87fcf9974fd1e3830`) for now.
301
+ For :code:`Qwen2-VL`, the latest release of :code:`huggingface/transformers` doesn't work yet, so we need to use a developer version (:code:`21fac7abba2a37fae86106f87fcf9974fd1e3830`) for now.
302
This can be installed by running the following command:
303
304
.. code-block:: bash