THUDM / slimeLinks
slime is a LLM post-training framework aiming for RL Scaling.
☆553Updated this week
Alternatives and similar repositories for slime
Users that are interested in slime are comparing it to the libraries listed below
Sorting:
- Super-Efficient RLHF Training of LLMs with Parameter Reallocation☆305Updated 2 months ago
- A flexible and efficient training framework for large-scale alignment tasks☆385Updated this week
- VeOmni: Scaling any Modality Model Training to any Accelerators with PyTorch native Training Framework☆370Updated this week
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆524Updated last month
- ☆193Updated 2 months ago
- An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models☆1,411Updated this week
- A visuailzation tool to make deep understaning and easier debugging for RLHF training.☆224Updated 4 months ago
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆285Updated 2 months ago
- Fast inference from large lauguage models via speculative decoding☆773Updated 10 months ago
- ByteCheckpoint: An Unified Checkpointing Library for LFMs☆224Updated this week
- Ring attention implementation with flash attention☆800Updated last week
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.☆457Updated 11 months ago
- A lightweight reproduction of DeepSeek-R1-Zero with indepth analysis of self-reflection behavior.☆244Updated 2 months ago
- 📰 Must-read papers on KV Cache Compression (constantly updating 🤗).☆468Updated 2 weeks ago
- InternEvo is an open-sourced lightweight training framework aims to support model pre-training without the need for extensive dependencie…☆393Updated last week
- ☆140Updated last week
- FlagScale is a large model toolkit based on open-sourced projects.☆321Updated this week
- Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (…☆136Updated this week
- Scalable toolkit for efficient model reinforcement☆478Updated this week
- ☆796Updated last month
- Codes for the paper "∞Bench: Extending Long Context Evaluation Beyond 100K Tokens": https://arxiv.org/abs/2402.13718☆341Updated 9 months ago
- Official Implementation of "Learning Harmonized Representations for Speculative Sampling" (HASS)☆42Updated 3 months ago
- ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search (NeurIPS 2024)☆643Updated 5 months ago
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆720Updated 3 months ago
- ☆142Updated 4 months ago
- Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling☆410Updated last month
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆92Updated 2 months ago
- Materials for learning SGLang☆475Updated this week
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆178Updated 3 weeks ago
- The related works and background techniques about Openai o1☆223Updated 6 months ago