ISEEKYAN / verl_megatron_practiceLinks
(best/better) practices of megatron on veRL and tuning guide
☆98Updated last month
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☆149Updated this week
- Async pipelined version of Verl☆125Updated 7 months ago
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆264Updated last month
- Training library for Megatron-based models☆158Updated last week
- Super-Efficient RLHF Training of LLMs with Parameter Reallocation☆322Updated 6 months ago
- siiRL: Shanghai Innovation Institute RL Framework for Advanced LLMs and Multi-Agent Systems☆224Updated this week
- A lightweight reinforcement learning framework that integrates seamlessly into your codebase, empowering developers to focus on algorithm…☆68Updated 2 months ago
- ☆47Updated 2 months ago
- Reproducing R1 for Code with Reliable Rewards☆264Updated 6 months ago
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training☆217Updated last year
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆111Updated 7 months ago
- Homepage for ProLong (Princeton long-context language models) and paper "How to Train Long-Context Language Models (Effectively)"☆236Updated last month
- 🔥 LLM-powered GPU kernel synthesis: Train models to convert PyTorch ops into optimized Triton kernels via SFT+RL. Multi-turn compilation…☆94Updated last month
- ☆65Updated 11 months ago
- ByteCheckpoint: An Unified Checkpointing Library for LFMs☆251Updated 3 months ago
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆206Updated 8 months ago
- Repository of LV-Eval Benchmark☆70Updated last year
- ☆120Updated 5 months ago
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆125Updated last week
- [NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection☆52Updated last year
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆244Updated 3 months ago
- ☆26Updated 2 months ago
- Official Implementation of "Learning Harmonized Representations for Speculative Sampling" (HASS)☆49Updated 7 months ago
- ☆83Updated 2 months ago
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆210Updated last month
- Utility scripts for PyTorch (e.g. Make Perfetto show some disappearing kernels, Memory profiler that understands more low-level allocatio…☆63Updated last month
- ☆19Updated 3 weeks ago
- SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs☆168Updated last month
- Best practices for training DeepSeek, Mixtral, Qwen and other MoE models using Megatron Core.☆123Updated last week
- A Comprehensive Survey on Long Context Language Modeling☆199Updated 4 months ago