Pinned Repositories
REST
REST: Retrieval-Based Speculative Decoding, NAACL 2024
Spec-Bench
Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)
FastChat
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
hqq
Official implementation of Half-Quadratic Quantization (HQQ)
dlwpt-code
Code for the book Deep Learning with PyTorch by Eli Stevens, Luca Antiga, and Thomas Viehmann.
hqq
Official implementation of Half-Quadratic Quantization (HQQ)
jekyll-cayman-theme
A Jekyll theme for the responsive theme for GitHub Pages http://jasonlong.github.io/cayman-theme/
EAGLE
Official Implementation of EAGLE-1 and EAGLE-2
Ouroboros
Ouroboros: Speculative Decoding with Large Model Enhanced Drafting
Hydra
reflectionie's Repositories
reflectionie/dlwpt-code
Code for the book Deep Learning with PyTorch by Eli Stevens, Luca Antiga, and Thomas Viehmann.
reflectionie/hqq
Official implementation of Half-Quadratic Quantization (HQQ)
reflectionie/jekyll-cayman-theme
A Jekyll theme for the responsive theme for GitHub Pages http://jasonlong.github.io/cayman-theme/