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, 09:30 UTC
[Doc] Update multi-input support (#9906)
Cyrus Leung committed
Nov 1, 2024 at 15:34 UTC
d3aa2a8b2f93f50ed40fe7d8617701a2294a13e4
1 file changed
+2
-2
docs/source/models/supported_models.rst
+2
-2
@@ -466,7 +466,7 @@ Text Generation
466
- ✅︎
467
* - :code:`LlavaOnevisionForConditionalGeneration`
468
- LLaVA-Onevision
469
- - T + I\ :sup:`+` + V
469
+ - T + I\ :sup:`+` + V\ :sup:`+`
470
- :code:`llava-hf/llava-onevision-qwen2-7b-ov-hf`, :code:`llava-hf/llava-onevision-qwen2-0.5b-ov-hf`, etc.
471
-
472
- ✅︎
@@ -478,7 +478,7 @@ Text Generation
478
- ✅︎
479
* - :code:`MllamaForConditionalGeneration`
480
- Llama 3.2
481
- - T + I
481
+ - T + I\ :sup:`+`
482
- :code:`meta-llama/Llama-3.2-90B-Vision-Instruct`, :code:`meta-llama/Llama-3.2-11B-Vision`, etc.
483
-
484
-