NVIDIA/Model-Optimizer
A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.
About the project
NVIDIA library for compressing and accelerating models: quantization, pruning, distillation, NAS and speculative decoding with export to TensorRT-LLM, vLLM, SGLang. For ML engineers preparing models for deployment.
Useful for
- Quantize an LLM to FP8 or NVFP4 to speed up vLLM inference
- Compress a model via pruning and distillation while keeping quality
- Export an optimized checkpoint to TensorRT-LLM or SGLang
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 25 stars so far today, about 42 expected by the end of the day. The usual pace is 10 per day, so that's 4.2× as much.
- Over the last two days the pace is 5.2× that of the previous week and a half.
- GitHub Trending today: #5, +22 stars.
- GitHub Trending Python today: #3, +22 stars.
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 3,886
- Today
- 25 · ≈ 42 by evening
- Forks
- 621
- Issues and pull requests
- 2,523
- Watchers
- 32
- Language
- Python
- License
- Apache-2.0
- Latest release
- 0.47.0 · September 23, 2026
- Created
- April 23, 2024
- Last push
- September 24, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Spotted in
- September 24, 2026GitHub Trending today: #5, +22 stars; GitHub Trending Python today: #3, +22 stars
Share
README badge
Paste it into your README — the badge shows the current magnitude and links to this page.
[](https://gitnova.dev/en/r/NVIDIA/Model-Optimizer)Similar by description
-
1.6
microsoft/onnxruntime
Cross-platform accelerator for ML inference and training. Runs models from PyTorch, TensorFlow, scikit-learn and others via the ONNX format with graph optimizations and hardware acceleration.
-
1.6
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.
-
1.1
MiaAI-Lab/DeepSeek-v4.1-Flash-EXL3-2x-DGX-Sparks
A local EXL3 2.9 bpw checkpoint of DeepSeek-V4.1-Flash (196 GiB, 39 shards) served via an OpenAI-compatible vLLM API on a 2x NVIDIA GB10 (DGX Spark) kit with tensor-parallel 2. Includes DSpark speculative decoding and…
-
1.1
hao-ai-lab/FastVideo
A framework for accelerated video generation: post-training (distillation, LoRA, sparse attention) and fast inference of diffusion video models on GPU and Apple Silicon.
-
1.3
deepseek-ai/DeepSpec
Full-stack pipeline for training and evaluating draft models for speculative decoding: data preparation, training against a target-model cache, and acceptance measurement on benchmarks. Supports DSpark, DFlash and…
-
3.0
AlibabaResearch/SparkDiffusion
A video-generation acceleration framework for Diffusion Transformer models, combining sparse low-rank attention (RoLa), few-step distillation (CrossDistill) and custom operators to deliver 200×+ inference speedups for…