# NVIDIA/TensorRT-LLM

> NVIDIA library for optimizing inference of large language models and visual generative models on GPUs, with a Python API, specialized kernels, and an efficient C++/Python runtime.

- Magnitude: 1.6 out of 10 — Steady
- Stars: 14,746 total · +1 star on 2026-09-30 (UTC), ≈ 4 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Python · Created: 2023-08-16 · Last push: 2026-09-30
- GitHub: https://github.com/NVIDIA/TensorRT-LLM · Homepage: https://nvidia.github.io/TensorRT-LLM · Page: https://gitnova.dev/en/r/NVIDIA/TensorRT-LLM

## Useful for

- Deploy a high-throughput LLM inference server on NVIDIA GPUs
- Speed up video and image generation with quantization and optimized kernels
- Configure speculative decoding and KV cache to reduce latency

## Why it’s here

- 1 star so far today, about 5 expected by the end of the day.
- Recent forks include notable developers: @jiazhihao (610 followers).

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 2,782
- Issues and pull requests: 19,485
- Watchers: 123
- Average over the last week: 7 per day
- Usual pace: 10 per day
- Latest release: v1.3.0rc29 (2026-09-29)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-10-05 … 2026-11-03: None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None

## Magnitude by day, last 12 days

09-19 2.0, 09-20 1.8, 09-21 1.6, 09-22 1.5, 09-23 1.9, 09-24 1.6, 09-25 1.5, 09-26 1.4, 09-27 1.6, 09-28 1.7, 09-29 1.9, 09-30 1.8

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-09-30 10:54 UTC, updated every 30 minutes.