ISEEKYAN / verl_megatron_practiceLinks
(best/better) practices of megatron on veRL and tuning guide
☆86Updated 3 weeks ago
Alternatives and similar repositories for verl_megatron_practice
Users that are interested in verl_megatron_practice are comparing it to the libraries listed below
Sorting:
- Bridge Megatron-Core to Hugging Face/Reinforcement Learning☆126Updated this week
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆207Updated last week
- Async pipelined version of Verl☆117Updated 5 months ago
- Super-Efficient RLHF Training of LLMs with Parameter Reallocation☆315Updated 4 months ago
- A lightweight reinforcement learning framework that integrates seamlessly into your codebase, empowering developers to focus on algorithm…☆68Updated 3 weeks ago
- Repository of LV-Eval Benchmark☆70Updated last year
- Best practices for training DeepSeek, Mixtral, Qwen and other MoE models using Megatron Core.☆93Updated this week
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training☆216Updated last year
- siiRL: Shanghai Innovation Institute RL Framework for Advanced LLMs and Multi-Agent Systems☆211Updated this week
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆111Updated 5 months ago
- ☆65Updated 9 months ago
- ☆47Updated last month
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆110Updated 6 months ago
- Reproducing R1 for Code with Reliable Rewards☆256Updated 4 months ago
- Homepage for ProLong (Princeton long-context language models) and paper "How to Train Long-Context Language Models (Effectively)"☆226Updated last week
- ☆23Updated 2 weeks ago
- ☆119Updated 3 months ago
- [NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection☆51Updated 10 months ago
- ByteCheckpoint: An Unified Checkpointing Library for LFMs☆245Updated 2 months ago
- Estimate MFU for DeepSeekV3☆24Updated 8 months ago
- ☆31Updated last month
- Training library for Megatron-based models☆85Updated this week
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆202Updated 7 months ago
- A flexible and efficient training framework for large-scale alignment tasks☆425Updated this week
- PyTorch bindings for CUTLASS grouped GEMM.☆146Updated 3 weeks ago
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆208Updated last week
- Utility scripts for PyTorch (e.g. Memory profiler that understands more low-level allocations such as NCCL)☆53Updated last week
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆239Updated last month
- ☆43Updated 4 months ago
- ☆147Updated 6 months ago