NVIDIA / Star-AttentionLinks
Efficient LLM Inference over Long Sequences
☆391Updated 2 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:
- LLM KV cache compression made easy☆604Updated this week
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆490Updated 7 months ago
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆377Updated last year
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆747Updated 6 months ago
- KV cache compression for high-throughput LLM inference☆136Updated 7 months ago
- A safetensors extension to efficiently store sparse quantized tensors on disk☆157Updated this week
- ArcticInference: vLLM plugin for high-throughput, low-latency inference☆235Updated this week
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆230Updated 9 months ago
- 🚀 Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash…☆265Updated last month
- Code for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024☆334Updated 4 months ago
- A family of compressed models obtained via pruning and knowledge distillation☆350Updated 10 months ago
- TransMLA: Multi-Head Latent Attention Is All You Need☆353Updated last week
- kernels, of the mega variety☆486Updated 3 months ago
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆374Updated this week
- Load compute kernels from the Hub☆271Updated this week
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆188Updated 2 months ago
- ☆197Updated 4 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆124Updated 9 months ago
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆319Updated 7 months ago
- Advanced Quantization Algorithm for LLMs and VLMs, with support for CPU, Intel GPU, CUDA and HPU.☆614Updated this week
- 🚀 Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.☆209Updated last week
- VPTQ, A Flexible and Extreme low-bit quantization algorithm☆653Updated 4 months ago
- A throughput-oriented high-performance serving framework for LLMs☆886Updated last month
- Applied AI experiments and examples for PyTorch☆295Updated 3 weeks ago
- Fast low-bit matmul kernels in Triton☆357Updated this week
- [ACL 2025 Main] EfficientQAT: Efficient Quantization-Aware Training for Large Language Models☆301Updated 3 months ago
- scalable and robust tree-based speculative decoding algorithm☆357Updated 7 months ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆319Updated last year
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆165Updated last year
- [ICLR2025 Spotlight] MagicPIG: LSH Sampling for Efficient LLM Generation☆233Updated 8 months ago