remotion-dev/remotion
docker-desktop-windows/docker-desktop
stablyai/orca
cslol-manager/ltk-manager
thedotmack/claude-mem Collection
Model Compression
The Model Compression collection tracks 12 curated open-source projects, 10 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 · 36m| # | Repository | Stars | 24h | 7d | 30d | Trend | Mentions | Actions |
|---|---|---|---|---|---|---|---|---|
| 01 |  ggml-org/llama.cpp LLM inference in C/C++ | 121.7K | — | +608+0.5% | +3.6K+3.0% |      live on Hacker News | ||
| 02 |  deepspeedai/DeepSpeed DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective. | 42.8K | +4+0.0% | +62+0.1% | +237+0.6% | live on X / Twitter | ||
| 03 |  microsoft/onnxruntime ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator | 21.2K | +4+0.0% | +55+0.3% | +263+1.3% | | ||
| 04 |  pytorch/executorch On-device AI across mobile, embedded and edge for PyTorch | 4.8K | +1+0.0% | +17+0.4% | +76+1.6% | | ||
| 05 |  mlc-ai/mlc-llm Universal LLM Deployment Engine with ML Compilation | 23K | — | +29+0.1% | +151+0.7% | | ||
| 06 |  hpcaitech/ColossalAI Making large AI models cheaper, faster and more accessible | 41.4K | +3+0.0% | +13+0.0% | +56+0.1% | | ||
| 07 |  bitsandbytes-foundation/bitsandbytes Accessible large language models via k-bit quantization for PyTorch. | 8.3K | +1+0.0% | +6+0.1% | +54+0.7% | live on X / Twitter | ||
| 08 |  huggingface/optimum 🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization tools | 3.5K | -1-0.0% | +4+0.1% | +27+0.8% | | ||
| 09 |  AutoGPTQ/AutoGPTQ An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm. | 5.1K | — | +2+0.0% | +10+0.2% | live on X / Twitter | ||
| 10 |  IST-DASLab/gptq Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers". | 2.3K | +1+0.0% | +4+0.2% | +11+0.5% | | ||
| 11 | deepspeedai/DeepSpeed-MII No description published. | 0 | — | — | — | | ||
| 12 | qwopqwop200/GPTQ-for-LLaMa No description published. | 0 | — | — | — | |