This repository, deepspeed-grpo-qlora-vllm, provides a complete framework for fine-tuning LLMs using Group Relative Policy Optimization (GRPO) on 4-bit quantized models (QLoRA). It utilizes DeepSpeed ZeRO-3 for scalable training and integrates with a VLLM server to dynamically serve the fine-tuned LoRA adapters.
☆13Jul 15, 2025Updated last year
Alternatives and similar repositories for deepspeed-grpo-qlora-vllm
Users that are interested in deepspeed-grpo-qlora-vllm are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Reproducibility study of the paper: "InPars Toolkit: A Unified and Reproducible Synthetic Data Generation Pipeline for Neural Information…☆12Feb 11, 2025Updated last year
- Nano vLLM Triton☆14Aug 27, 2025Updated last year
- Train an agent to generate high quality summaries☆46Jan 29, 2026Updated 8 months ago
- ☆10Feb 22, 2023Updated 3 years ago
- simple grpo☆13May 28, 2025Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- [NeurIPS 2023] Training Energy-Based Normalizing Flow with Score-Matching Objectives☆10Jun 15, 2026Updated 4 months ago
- Pytorch code for Sampling in Combinatorial Spaces with SurVAE Flow Augmented MCMC☆11Mar 1, 2021Updated 5 years ago
- High-performance runtime for real-time multimodal generation and world models—streaming inference, stateful sessions, and distributed GP…☆35Sep 26, 2026Updated 3 weeks ago
- Code for "Semantic Perturbations with Normalizing Flows for Improved Generalization"☆11Jul 13, 2021Updated 5 years ago
- Example Code for the Conditional Action Trees Paper☆13May 24, 2021Updated 5 years ago
- Official repository for the preprint "On Sampling with Approximate Transport Maps" in PyTorch.☆10May 28, 2023Updated 3 years ago
- ☆20Sep 6, 2025Updated last year
- Normalize CJK characters in text☆14Sep 30, 2025Updated last year
- Porting Postgres Server to WASM [WIP]☆16Mar 6, 2021Updated 5 years ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- A simple "Be My Eyes" web app with a llama.cpp/llava backend☆15Jan 25, 2024Updated 2 years ago
- Repository for Skill Set Optimization☆14Jul 26, 2024Updated 2 years ago
- ☆11Aug 26, 2024Updated 2 years ago
- Bayesian Meta Sampling for Fast Uncertainty Adaptation☆10Jun 27, 2020Updated 6 years ago
- Source code for "Continuous Regularized Wasserstein Barycenters" [NeurIPS 2020].☆16Nov 4, 2020Updated 5 years ago
- Unofficial implementation of Variational Diffusion Models in PyTorch (Lightning)☆12Aug 31, 2023Updated 3 years ago
- ☆16Jul 15, 2025Updated last year
- Official code for SA-Solver: Stochastic Adams Solver for Fast Sampling of Diffusion Models (NeurIPS 2023)☆15Mar 4, 2024Updated 2 years ago
- ☆13Oct 13, 2025Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- To mitigate position bias in LLMs, especially in long-context scenarios, we scale only one dimension of LLMs, reducing position bias and …☆13Jun 18, 2024Updated 2 years ago
- ☆17Dec 3, 2024Updated last year
- ☆17Mar 2, 2023Updated 3 years ago
- Benchmarking Deepseek R1 API response speeds across different providers for performance comparison.☆10Feb 15, 2025Updated last year
- ☆41Aug 1, 2025Updated last year
- torch implementation of diloco☆30Jul 17, 2026Updated 3 months ago
- Official repo: “Oh LLM, I’m Asking Thee, Please Give Me a Decision Tree”: Zero-Shot Decision Tree Induction and Embedding with Large Lang…☆21Aug 10, 2026Updated 2 months ago
- ROS driver for DJI/Ryze Tello drones☆10Jun 23, 2021Updated 5 years ago
- This repository provides a framework to serve LLM(Large Language Model) based applications such as Chatbot.☆18Apr 20, 2023Updated 3 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Demo code samples for the course DS 303 Introduction to Machine Learning, Spring 2021, IIT Bombay☆16Mar 22, 2021Updated 5 years ago
- Gradient Estimation with Discrete Stein Operators (NeurIPS 2022)☆18Nov 14, 2023Updated 2 years ago
- Explore training for quantized models☆29Jul 12, 2025Updated last year
- CHIQ: Contextual History Enhancement for Improving Query Rewriting in Conversational Search. A code base for EMNLP 2024 paper.☆13Aug 27, 2025Updated last year
- Meta-Reinforcement Learning with Self-Reflection☆38Mar 26, 2026Updated 6 months ago
- NeurIPS'23: Energy Discrepancies: A Score-Independent Loss for Energy-Based Models☆18Oct 22, 2024Updated 2 years ago
- Implementation of an RL based agent, which utilizes Q-Learning to develop a policy for effectively solving a 3x3x3 rubiks cube☆19Mar 12, 2019Updated 7 years ago