Collection

Model Compression

The Model Compression collection tracks 12 curated open-source projects, 3 of them live on TrendingRepo right now — ranked by a cross-source momentum score blending GitHub star velocity with mentions on Hacker News, X, Bluesky, Product Hunt and Dev.to.

Live · top 12 repos · sorted by momentum across 24H

LIVE · 11m

Velocity period:24h 7d 30dClick to re-sort top 12

#	Repository	Stars	24h	7d	30d	Mentions
01	deepspeedai/DeepSpeed DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.	42.5K	—	+40+0.1%	+225+0.5%
02	bitsandbytes-foundation/bitsandbytes Accessible large language models via k-bit quantization for PyTorch.	8.3K	—	+10+0.1%	+80+1.0%	live on X / Twitter
03	AutoGPTQ/AutoGPTQ An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.	5.1K	-1-0.0%	+1+0.0%	+13+0.3%
04	deepspeedai/DeepSpeed-MII No description published.	0	—	—	—
05	ggml-org/llama.cpp No description published.	0	—	—	—
06	hpcaitech/ColossalAI No description published.	0	—	—	—
07	huggingface/optimum No description published.	0	—	—	—
08	IST-DASLab/gptq No description published.	0	—	—	—
09	microsoft/onnxruntime No description published.	0	—	—	—
10	mlc-ai/mlc-llm No description published.	0	—	—	—
11	pytorch/executorch No description published.	0	—	—	—
12	qwopqwop200/GPTQ-for-LLaMa No description published.	0	—	—	—

Showing 12 of 12 · ranked by momentum, velocity, and consensus

Prev Next