mdy666 / Qwen-Native-Sparse-AttentionLinks
qwen-nsa
☆74Updated 4 months ago
Alternatives and similar repositories for Qwen-Native-Sparse-Attention
Users that are interested in Qwen-Native-Sparse-Attention are comparing it to the libraries listed below
Sorting:
- Efficient Mixture of Experts for LLM Paper List☆97Updated this week
- ☆117Updated 2 months ago
- SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs☆147Updated 3 weeks ago
- The Official Implementation of Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference☆89Updated 2 months ago
- ☆143Updated last month
- [ICLR 2025] Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models☆125Updated last month
- D^2-MoE: Delta Decompression for MoE-based LLMs Compression☆64Updated 5 months ago
- ☆55Updated last month
- ☆98Updated 4 months ago
- Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme☆138Updated 4 months ago
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆107Updated 4 months ago
- ☆29Updated 5 months ago
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆231Updated 2 weeks ago
- [ICLR 2024 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"☆91Updated 2 months ago
- A lightweight reinforcement learning framework that integrates seamlessly into your codebase, empowering developers to focus on algorithm…☆48Updated last week
- LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification☆62Updated last month
- DeepSeek Native Sparse Attention pytorch implementation☆90Updated 2 weeks ago
- Source code for the paper "LongGenBench: Long-context Generation Benchmark"☆23Updated 10 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆133Updated 3 months ago
- [ICML24] Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for LLMs☆92Updated 9 months ago
- Due to the huge vocaburary size (151,936) of Qwen models, the Embedding and LM Head weights are excessively heavy. Therefore, this projec…☆26Updated last year
- ☆199Updated 4 months ago
- ☆45Updated 2 months ago
- Efficient triton implementation of Native Sparse Attention.☆208Updated 3 months ago
- ☆45Updated 9 months ago
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆188Updated 2 months ago
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆219Updated last month
- Multi-Candidate Speculative Decoding☆36Updated last year
- Inference Code for Paper "Harder Tasks Need More Experts: Dynamic Routing in MoE Models"☆60Updated last year
- Official PyTorch implementation of the paper "dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching" (dLLM-Cache…☆140Updated 2 weeks ago