---
tags: Concept, CCS, ZH
title: CCS Image-Triton Inference Server | zh
GA: UA-155999456-1
---
{%hackmd @docsharedstyle/default %}
{%hackmd @docsharedstyle/twccheader-zh %}
{%hackmd @docsharedstyle/ccs-image-icon-size %}
# <img class="ccsimgicon" src="https://cos.twcc.ai/SYS-MANUAL/uploads/upload_f55059e9d0a6ac45c44bcc0ec1bebff5.png"> Triton Inference Server
TWCC 提供 NGC’s Triton Inference Server 立即可用的工作環境。Triton 推理伺服器透過 HTTP 端點提供推理服務，能讓遠端的用戶對伺服器管理的各式模型提出推理運算的需求。除了提供 Triton 推理服務的容器環境，亦提供 C++ 與 Python 的用戶端函式庫，以及 GitHub 上推理伺服器的相關文件。
## <i class="fa fa-sticky-note" aria-hidden="true"></i> <span class="ccsimglist">映像檔版本資訊</span>
:::info
{%hackmd @docsharedstyle/note-zh %}
`py3` 與 `py2` 為 Python 版本差異。
:::
<details class="docspoiler">
<summary><b>點我參考詳細版本套件資訊</b></summary>
- [tritonserver-22.08-py3](https://docs.nvidia.com/deeplearning/triton-inference-server/release-notes/rel_22-05.html#rel_22-08)
- [tritonserver-22.05-py3](https://docs.nvidia.com/deeplearning/triton-inference-server/release-notes/rel_22-05.html#rel_22-05)
- [tritonserver-22.02-py3](https://docs.nvidia.com/deeplearning/triton-inference-server/release-notes/rel_22-02.html#rel_22-02)
- [tritonserver-21.11-py3](https://docs.nvidia.com/deeplearning/triton-inference-server/release-notes/rel_21-11.html#rel_21-11)
- [tritonserver-21.08-py3](https://docs.nvidia.com/deeplearning/triton-inference-server/release-notes/rel_21-08.html#rel_21-08)
- [tritonserver-21.06-py3](https://docs.nvidia.com/deeplearning/triton-inference-server/release-notes/rel_21-06.html#rel_21-06)
- [tritonserver-21.02-py3](https://docs.nvidia.com/deeplearning/triton-inference-server/release-notes/rel_21-02.html#rel_21-02)
- [tensorrtserver-20.02-py3](https://docs.nvidia.com/deeplearning/triton-inference-server/release-notes/rel_20-02.html#rel_20-02)
- [tensorrtserver-19.02-py3-v1](https://docs.nvidia.com/deeplearning/triton-inference-server/release-notes/rel_19-02.html#rel_19-02)
- [tensorrtserver-18.12-py3-v1](https://docs.nvidia.com/deeplearning/triton-inference-server/release-notes/rel_18.12.html#rel_18.12)
- [tensorrtserver-18.10-py3-v1](https://docs.nvidia.com/deeplearning/triton-inference-server/release-notes/rel_18.10.html#rel_18.10)
- [tensorrtserver-18.08.1-py2/py3-v1](https://docs.nvidia.com/deeplearning/triton-inference-server/release-notes/rel_18.08.html#rel_18.08)
</details>