ModelTC/LightCompress

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

⭐ 742 ⑂ 77 Python Apache-2.0 · 2026-05-14推送

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

742

Watchers

0

贡献者

0

Commits

0

Releases

42

Open Issues

2026-05-14

最近推送

原文中文

暂无 README