ModelTC/LightCompress

[EMNLP 2024 & AAAI 2026] A powerful toolkit for compressing large models including LLMs, VLMs, and video generative models.

↗ Open on GitHub

Stars

747

Forks

78

Language

Python

License

Apache-2.0

Last push

4 months ago

Python tool llm large-language-models vllm wan benchmark quantization evaluation deployment mixtral pruning deepseek-v3 token-reduction awq internlm2 smoothquant token-merging token-pruning

No related intel yet

This repo has not appeared in any of the sources the radar tracks. The collector runs on a schedule — check back once it covers this repo.