Dhruva Bansal's repositories
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
lorax
Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs
llama-recipes
Examples and recipes for Llama 2 model
ChirpBrief
Chat GPT is all you need
detr
End-to-End Object Detection with Transformers
DhruvaBansal00.github.io
Code for portfolio website
LINK
Code and data for our RSS 2021 paper "Learning Instance-Level N-Ary Knowledge for Robots Operating in Everyday Environments" Resources
system-design-primer
Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.
DMP-Imperfect-Demonstrations
Training and Analyzing DMPs and PPO for augmenting to imperfect demonstrations.
comanipulation
Collaborative Manipulation Project - Trajectory Adaptation
Deep-Learning-for-ASLR
Implementing Transformers and GRUs for American Sign Language Recognition. Comparing results with HMM-based models.
ConfidentMT
Predicting translation confidence for Transformer-based Neural Machine Translators.
flores
Analyzing FLoRes MT Benchmark
kaldi
This is the official location of the Kaldi project.
RecommendationGenerator
Recommending products based on explicit feedback