NVIDIA / Star-Attention
Efficient LLM Inference over Long Sequences
☆365Updated last month
Alternatives and similar repositories for Star-Attention:
Users that are interested in Star-Attention are comparing it to the libraries listed below
- LLM KV cache compression made easy☆440Updated this week
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆435Updated last month
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆611Updated 2 weeks ago
- Fast Matrix Multiplications for Lookup Table-Quantized LLMs☆232Updated last month
- Advanced Quantization Algorithm for LLMs/VLMs.☆394Updated this week
- Ring attention implementation with flash attention☆711Updated 3 weeks ago
- 🚀 Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash…☆232Updated 2 weeks ago
- A throughput-oriented high-performance serving framework for LLMs☆773Updated 6 months ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆447Updated last month
- Fast low-bit matmul kernels in Triton☆267Updated this week
- Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"☆223Updated last month
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆336Updated 7 months ago
- Applied AI experiments and examples for PyTorch☆249Updated this week
- ☆393Updated 2 weeks ago
- A family of compressed models obtained via pruning and knowledge distillation☆330Updated 4 months ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆298Updated 8 months ago
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆201Updated 4 months ago
- [ICML 2024] CLLMs: Consistency Large Language Models☆386Updated 4 months ago
- Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, spars…☆307Updated 3 months ago
- A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.☆524Updated last month
- Cataloging released Triton kernels.☆204Updated 2 months ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆317Updated this week
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆259Updated 4 months ago
- Implementation of 💍 Ring Attention, from Liu et al. at Berkeley AI, in Pytorch☆506Updated 4 months ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆262Updated 5 months ago
- ☆180Updated 5 months ago
- KV cache compression for high-throughput LLM inference☆117Updated last month
- EfficientQAT: Efficient Quantization-Aware Training for Large Language Models☆255Updated 5 months ago