NVIDIA / Star-AttentionLinks
Efficient LLM Inference over Long Sequences
☆376Updated this week
Alternatives and similar repositories for Star-Attention
Users that are interested in Star-Attention are comparing it to the libraries listed below
Sorting:
- LLM KV cache compression made easy☆493Updated 3 weeks ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆686Updated 2 months ago
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆686Updated 2 months ago
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆355Updated 9 months ago
- 🚀 Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash…☆249Updated this week
- kernels, of the mega variety☆329Updated this week
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆463Updated 3 months ago
- A throughput-oriented high-performance serving framework for LLMs☆814Updated 3 weeks ago
- Advanced Quantization Algorithm for LLMs and VLMs, with support for CPU, Intel GPU, CUDA and HPU. Seamlessly integrated with Torchao, Tra…☆483Updated this week
- Fast low-bit matmul kernels in Triton☆303Updated last week
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆305Updated 11 months ago
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,040Updated this week
- Perplexity GPU Kernels☆324Updated 2 weeks ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆384Updated this week
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆166Updated last week
- TransMLA: Multi-Head Latent Attention Is All You Need☆284Updated this week
- Code for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024☆301Updated last month
- ☆193Updated 3 weeks ago
- Materials for learning SGLang☆424Updated last week
- Ring attention implementation with flash attention☆771Updated last week
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆506Updated last week
- A safetensors extension to efficiently store sparse quantized tensors on disk☆117Updated this week
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆203Updated 2 weeks ago
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆211Updated 6 months ago
- A family of compressed models obtained via pruning and knowledge distillation☆341Updated 6 months ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆263Updated 7 months ago
- [ACL 2025 Main] EfficientQAT: Efficient Quantization-Aware Training for Large Language Models☆270Updated last week
- ☆322Updated last year
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆291Updated 6 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆107Updated 2 weeks ago