GitHub Trending repo Repositories Mar 28 4 views

Argonaut790/fused-turboquant: Fused Triton kernels for TurboQuant KV cache compression — 2-4 bit quantization with RHT rotation. Drop-in HuggingFace & vLLM integration. Up to 4.9x KV cache compression for Llama, Qwen, Mistral, and more.

by Argonaut790

Fused Triton kernels for TurboQuant KV cache compression — 2-4 bit quantization with RHT rotation. Drop-in HuggingFace & vLLM integration. Up to 4.9x KV cache compression for Llama, Qwen, Mistral, and more.

Read Original
API Hugging Face Mistral

Metadata

Stars
5
Language
Python
Watchers
5
Open Issues
4
License
Apache-2.0

Related

GitHub Trending repo 7h ago

BasZ4ll/Stable-Diffusion-WebUI: Stable Diffusion: webui automatic1111 download free, comfyui setup guide, sdxl checkpoint safetensors, lora model civitai, controlnet extension github. SD WebUI Forge launcher, low VRAM optimization, xformers command line arguments, python torch cuda error fix, out of memory solution, txt2img img2img, inpainting, realesrgan upscaler, local pc insta

Stable Diffusion: webui automatic1111 download free, comfyui setup guide, sdxl checkpoint safetensors, lora model civitai, controlnet extension github. SD WebUI Forge launcher, low...

56
GitHub Trending repo 16h ago

rajchandran006-ops/RFD-Classification-Machine-Learning-Project: RFD Classification Machine Learning project developed using Python and Jupyter Notebook. This project includes data preprocessing, exploratory data analysis, feature engineering, and implementation of multiple classification algorithms such as Logistic Regression, Random Forest, SVM, KNN, and Naive Bayes for prediction and accuracy evaluation.

RFD Classification Machine Learning project developed using Python and Jupyter Notebook. This project includes data preprocessing, exploratory data analysis, feature engineering, a...

41