GitHub Trending repo Repositories Jul 5 1 views

avifenesh/bw24: From-scratch Rust+CUDA LLM inference engine for RTX 5090 (sm_120a) — NVFP4, MoE, MTP speculative decoding, tuned against measured hardware limits

by avifenesh

From-scratch Rust+CUDA LLM inference engine for RTX 5090 (sm_120a) — NVFP4, MoE, MTP speculative decoding, tuned against measured hardware limits

Read Original
AI Hardware LLM NVIDIA

Metadata

Stars
91
Forks
1
Language
Rust
Watchers
91
License
MIT

Related

GitHub Trending repo 17h ago

ramyadharshinimurugaprakash-commits/Titanic-Preprocessing: This project performs Exploratory Data Analysis (EDA) and data preprocessing on the Titanic dataset using Python in Google Colab. It includes data cleaning, handling missing values, statistical analysis, data visualization, feature engineering, and dataset preparation using Pandas and NumPy for future machine learning applications.

This project performs Exploratory Data Analysis (EDA) and data preprocessing on the Titanic dataset using Python in Google Colab. It includes data cleaning, handling missing values...

39