search

NVIDIA / TensorRT-LLM

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.
https://nvidia.github.io/TensorRT-LLM
Apache License 2.0
8.2k stars 909 forks source link

InternVL-Chat-V1.5 support #1567

Open chiquitita-101 opened 4 months ago

chiquitita-101 commented 4 months ago

pleaseeeeee, InternVL-Chat-V1.5 surpasses many proprietary multi-modal models, very powerful, pleaseeeee.

diandianliu commented 3 months ago

Hi, Is InternVL-Chat-V1.5 suported now?

nv-guomingz commented 3 months ago

Hi, Is InternVL-Chat-V1.5 suported now?

Hi @AdamzNV @ncomly-nvidia @juney-nvidia , would please add some comments here?

AdamzNV commented 3 months ago

We don't support this model yet. According to download statistics from Hugging Face, its popularity has been declining for the past half month.

Hukongtao commented 2 months ago

mark

LIMr1209 commented 1 month ago

mark

AmazDeng commented 2 weeks ago

We don't support this model yet. According to download statistics from Hugging Face, its popularity has been declining for the past half month.

@AdamzNV Please take a look at this ranking list. The score of the InternVL model is in the top 2. https://rank.opencompass.org.cn/leaderboard-multimodal/?m=REALTIME