AMD | Anyscale | Purdue
Repositories
Rohan138/MAD
Rohan138/perf-eval
Performance benchmark & accuracy evaluation for vLLM
Rohan138/aiter
AI Tensor Engine for ROCm
Rohan138/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
Rohan138/MA-ALE2
Rohan138/rocm-libraries
super repo for rocm libraries
Rohan138/rt1-pytorch
Implementation of RT1 (Robotic Transformer) in Pytorch
Rohan138/recipes
Common recipes to run vLLM
Rohan138/sglang
SGLang is a fast serving framework for large language models and vision language models.
Rohan138/marl-baselines3
Multi-Agent Reinforcement Learning with Stable-Baselines3
Rohan138/optimum
🚀 Accelerate training and inference of 🤗 Transformers and 🤗 Diffusers with easy to use hardware optimization tools
Rohan138/llm-inference
Rohan138/accelerate
🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support
Rohan138/Rohan138.github.io
Rohan138/axolotl
Go ahead and axolotl questions
Rohan138/rllib-torch-maddpg
PyTorch implementation of MADDPG (Lowe et al.) in RLLib
Rohan138/Rohan138
Github Biography
Rohan138/tinygrad
You like pytorch? You like micrograd? You love tinygrad! ❤️
Rohan138/STORM
Rohan138/EfficientZero
Open-source codebase for EfficientZero, from "Mastering Atari Games with Limited Data" at NeurIPS 2021.
Rohan138/dreamerv3-torch
Implementation of Dreamer v3 in pytorch.
Rohan138/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Rohan138/staged-speculative-decoding
Rohan138/speculative-decoding
Explorations into some recent techniques surrounding speculative decoding
Rohan138/CoMBIne
Combined Model-Based and Inverse Reinforcement Learning for Generalization
Rohan138/aviary
Ray Aviary - evaluate multiple LLMs easily
Rohan138/langchain
⚡ Building applications with LLMs through composability ⚡
Rohan138/mbrl-lib
Library for Model Based RL
Rohan138/trlx
A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)