nvidia-modelopt
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.
View on Github
Activity
- Latest release
- 1w ago
- Total releases
- 41
- Cadence
- ~22 days
- Last 12 months
- 17
Reach
- Stars
- 5.4k
Details
- License
- Apache-2.0
- First release
- Apr 30, 2024
Releases
| Version | Released | |
|---|---|---|
0.48.0rc1
pre
| ||
0.47.0
minor
| ||
0.46.1
patch
| ||
0.46.0
minor
| ||
0.46.0rc2
pre
| ||
0.46.0rc1
pre
| ||
0.46.0rc0
pre
| ||
0.45.0
minor
| ||
0.44.0
minor
| ||
0.43.0
minor
| ||
0.42.0
minor
| ||
0.41.0
minor
| ||
0.41.0rc3
pre
| ||
0.41.0rc2
pre
| ||
0.41.0rc1
pre
| ||
0.40.0
minor
| ||
0.39.0
minor
| ||
0.37.0
minor
| ||
0.35.1
patch
| ||
0.35.0
minor
| ||
0.33.1
patch
| ||
0.33.0
minor
| ||
0.31.0
minor
| ||
0.29.0
minor
| ||
0.27.1
patch
| ||
0.27.0
minor
| ||
0.25.0
minor
| ||
0.23.2
patch
| ||
0.23.1
patch
| ||
0.23.0
minor
| ||
0.21.1
patch
| ||
0.21.0
minor
| ||
0.19.0
minor
| ||
0.17.0
minor
| ||
0.15.1
patch
| ||
0.15.0
minor
| ||
0.13.1
patch
| ||
0.13.0
minor
| ||
0.11.2
patch
| ||
0.11.1
patch
| ||
0.11.0
initial
|