NVIDIA / Star-AttentionLinks
Efficient LLM Inference over Long Sequences
☆392Updated 5 months ago
Alternatives and similar repositories for Star-Attention
Users that are interested in Star-Attention are comparing it to the libraries listed below
Sorting:
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆507Updated 9 months ago
- LLM KV cache compression made easy☆701Updated this week
- A safetensors extension to efficiently store sparse quantized tensors on disk☆210Updated 2 weeks ago
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆391Updated last year
- Code for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024☆347Updated 7 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆786Updated 8 months ago
- 🚀 Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash…☆271Updated last week
- KV cache compression for high-throughput LLM inference☆145Updated 9 months ago
- ArcticInference: vLLM plugin for high-throughput, low-latency inference☆327Updated this week
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆243Updated last year
- [ACL 2025 Main] EfficientQAT: Efficient Quantization-Aware Training for Large Language Models☆316Updated last week
- TransMLA: Multi-Head Latent Attention Is All You Need (NeurIPS 2025 Spotlight)☆413Updated 2 months ago
- Load compute kernels from the Hub☆337Updated last week
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆132Updated last year
- A family of compressed models obtained via pruning and knowledge distillation☆357Updated 3 weeks ago
- A framework for efficient model inference with omni-modality models☆466Updated this week
- VPTQ, A Flexible and Extreme low-bit quantization algorithm☆668Updated 7 months ago
- 🚀 Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.☆217Updated last week
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆196Updated 2 months ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆331Updated last year
- Efficient triton implementation of Native Sparse Attention.☆251Updated 6 months ago
- Fast low-bit matmul kernels in Triton☆401Updated last week
- Applied AI experiments and examples for PyTorch☆307Updated 3 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆170Updated last year
- [ICLR2025 Spotlight] MagicPIG: LSH Sampling for Efficient LLM Generation☆241Updated 11 months ago
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆335Updated last week
- ☆205Updated 6 months ago
- kernels, of the mega variety☆614Updated 2 months ago
- A throughput-oriented high-performance serving framework for LLMs☆918Updated last month
- ☆154Updated 9 months ago