volcengine / verl
veRL: Volcano Engine Reinforcement Learning for LLM
☆327Updated this week
Related projects ⓘ
Alternatives and complementary repositories for verl
- A flexible and efficient training framework for large-scale alignment tasks☆211Updated this week
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆364Updated this week
- Super-Efficient RLHF Training of LLMs with Parameter Reallocation☆123Updated this week
- Ring attention implementation with flash attention☆588Updated 2 weeks ago
- FlagScale is a large model toolkit based on open-sourced projects.☆178Updated this week
- ☆314Updated 4 months ago
- Official repository for LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformers☆195Updated 3 months ago
- ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search (NeurIPS 2024)☆325Updated last month
- Best practice for training LLaMA models in Megatron-LM☆628Updated 10 months ago
- Codes for the paper "∞Bench: Extending Long Context Evaluation Beyond 100K Tokens": https://arxiv.org/abs/2402.13718☆285Updated last month
- Zero Bubble Pipeline Parallelism☆283Updated last week
- InternEvo is an open-sourced lightweight training framework aims to support model pre-training without the need for extensive dependencie…☆310Updated this week
- 📰 Must-read papers and blogs on Speculative Decoding ⚡️☆477Updated this week
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.☆393Updated 3 months ago
- Fast inference from large lauguage models via speculative decoding☆577Updated 3 months ago
- A repository sharing the literatures about long-context large language models, including the methodologies and the evaluation benchmarks☆252Updated 3 months ago
- The related works and background techniques about Openai o1☆144Updated 2 weeks ago
- Inferflow is an efficient and highly configurable inference engine for large language models (LLMs).☆236Updated 8 months ago
- GPT-Fathom is an open-source and reproducible LLM evaluation suite, benchmarking 10+ leading open-source and closed-source LLMs as well a…☆349Updated 7 months ago
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆190Updated 3 weeks ago
- PyTorch bindings for CUTLASS grouped GEMM.☆68Updated 4 months ago
- Scalable toolkit for efficient model alignment☆624Updated this week
- ☆189Updated 6 months ago
- [ICML'24] Data and code for our paper "Training-Free Long-Context Scaling of Large Language Models"☆358Updated last month
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆176Updated this week
- The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.☆723Updated this week
- A PyTorch Native LLM Training Framework☆672Updated 2 months ago
- [ACL 2024] LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding☆672Updated 2 months ago
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.☆648Updated last month
- Large Context Attention☆642Updated 3 months ago