LLM-Manifold-Based-Compression-Techniques

Public

Research code for LLM Compression using Functional Algorithms, exploring stratified manifold learning, clustering, and compression techniques. Experiments span synthetic datasets (Swiss Roll, Manifold Singularities) and real-world text embeddings (DBpedia-14). The goal is to preserve semantic structure while reducing model complexity.

classical-clustering clustering cuda embeddings functional-algorithms hdbscan llm-compression manifold-learning pruning quantization

Creat：2025-07-26T02:11:44

Update：2025-09-12T12:03:15

https://github.com/meghanmane84/LLM-Manifold-Based-Compression-Techniques.git

Stars

Stars Increase

Related projects

Vllm

Hot

amd

A high-throughput and memory-efficient inference and serving engine for LLMs

59666

1年前

+458today

Sglang

Hot

cuda

SGLang is a fast serving framework for large language models and vision language models.

18679

6个月前

+179today

Kaldi

c-plus-plus

kaldi-asr/kaldi is the official location of the Kaldi project.

15156

6个月前

+15today

Open3D

Open3D: A Modern Library for 3D Data Processing

12844

6个月前

+22today

TensorRT LLM

Hot

blackwell

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and support state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in performant way.

11796

2个月前

+59today