stepfun-ai / Step3Links
☆439Updated 3 months ago
Alternatives and similar repositories for Step3
Users that are interested in Step3 are comparing it to the libraries listed below
Sorting:
- ByteCheckpoint: An Unified Checkpointing Library for LFMs☆254Updated this week
- A sparse attention kernel supporting mix sparse patterns☆391Updated 9 months ago
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆250Updated 3 months ago
- A framework for efficient model inference with omni-modality models☆466Updated this week
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training☆570Updated this week
- Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"☆713Updated last week
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆155Updated last month
- SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs☆175Updated 2 months ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆605Updated last month
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆507Updated 9 months ago
- Efficient triton implementation of Native Sparse Attention.☆251Updated 6 months ago
- Official PyTorch implementation of the paper "dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching" (dLLM-Cache…☆186Updated 2 weeks ago
- ☆207Updated last month
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆256Updated 4 months ago
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆498Updated last week
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆196Updated 2 months ago
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆275Updated 3 weeks ago
- DeepSeek Native Sparse Attention pytorch implementation☆108Updated 3 weeks ago
- ☆201Updated 2 weeks ago
- A curated list of recent papers on efficient video attention for video diffusion models, including sparsification, quantization, and cach…☆49Updated last month
- VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo☆1,374Updated this week
- A lightweight reinforcement learning framework that integrates seamlessly into your codebase, empowering developers to focus on algorithm…☆90Updated 3 months ago
- Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling☆456Updated 6 months ago
- 青稞Talk☆169Updated last week
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆356Updated 4 months ago
- mllm-npu: training multimodal large language models on Ascend NPUs☆94Updated last year
- ☆86Updated 5 months ago
- Super-Efficient RLHF Training of LLMs with Parameter Reallocation☆326Updated 7 months ago
- High performance inference engine for diffusion models☆96Updated 3 months ago
- FlagScale is a large model toolkit based on open-sourced projects.☆416Updated last week