mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
* feat: enhance trtllm serve multimodal 1. made the load_image and load_video asynchronous 2. add image_encoded input support to be compatible with genai-perf 3. support text-only on multimodal mdoels(currently, Qwen2-VL & Qwen2.5-VL) Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com> * add test Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com> * fix bandit Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com> * trimming uils Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com> * trimming for test Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com> * genai perf command fix Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com> * command fix Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com> * refactor chat_utils Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com> * stress test genai-perf command Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com> --------- Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com> |
||
|---|---|---|
| .. | ||
| source | ||
| Doxygen | ||
| make.bat | ||
| Makefile | ||
| README.md | ||
| requirements.txt | ||
Docs
This directory contains the stuff for building static html documentations based on sphinx.
Build the docs
Firstly, install the sphinx:
apt-get install python3-sphinx doxygen python3-pip graphviz
Secondly, install the packages:
python3 -m pip install -r ./requirements.txt
And then, make the docs:
doxygen Doxygen # build C++ docs
make html
And the finally the generated html pages will locate in the build/html directory.
Preview the docs locally
The basic way to preview the docs is using the http.serve:
cd build/html
python3 -m http.server 8081
And you can visit the page with your web browser with url http://localhost:8081.