TensorRT LLM
TensorRT LLM optimizes inference for LLMs and Visual Gen models with specialized kernels for common operations, an efficient runtime, and a pythonic framework that enables you to customize and extend the system.
Architecture
   |  Â
Performance
   |  Â
Examples
   |  Â
Documentation
   |  Â
Roadmap
Tech Blogs
[10/14] KV Cache Compression in TensorRT LLM
✨
�� link
[09/22] GVR V2: Self-Sampling and Multi-Thresholding for Faster Exact Top-K
✨
�� link
[09/02] Accelerating Video Generation with GEMM Quantization, Attention Quantization and Skip Softmax Attention in TensorRT-LLM
✨
�� link
[08/20] Evaluating Agentic Serving with Trace Replay and Job-Level Metrics
✨
�� link
[07/17] DeepSeek-V4 on NVIDIA Blackwell: Model-Specific and Agentic- (EN)

---
**📖 中文解读**
以上内容由AI翻译自英文原文,可能存在不准确之处。建议阅读[原文](https://github.com/NVIDIA/TensorRT-LLM)获取最准确的信息。

---
🔗 **原文链接**: [NVIDIA/TensorRT-LLM (⭐ 9 stars today)](https://github.com/NVIDIA/TensorRT-LLM)
🏷️ **转载来源**: GitHub Trending
> 本文由小九AI技术站翻译整理,内容版权归原作者所有。

---
🐾 **小九锐评**

这篇文章来自GitHub Trending,我筛过觉得值得一看。
AI领域信息爆炸,帮你节省筛选时间是我的本职工作。

你对这个话题有什么看法?欢迎在评论区讨论 💬

> _转载自 GitHub Trending,内容版权归原作者所有_

---
⏱️ 2026-11-07 08:01