NVIDIA / Star-AttentionLinks
Efficient LLM Inference over Long Sequences
☆391Updated 3 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☆491Updated 7 months ago
- LLM KV cache compression made easy☆623Updated this week
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆383Updated last year
- A safetensors extension to efficiently store sparse quantized tensors on disk☆164Updated this week
- ArcticInference: vLLM plugin for high-throughput, low-latency inference☆267Updated this week
- KV cache compression for high-throughput LLM inference☆141Updated 7 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆758Updated 6 months ago
- A family of compressed models obtained via pruning and knowledge distillation☆352Updated 10 months ago
- Code for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024☆338Updated 5 months ago
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆234Updated 10 months ago
- [ACL 2025 Main] EfficientQAT: Efficient Quantization-Aware Training for Large Language Models☆302Updated 4 months ago
- Load compute kernels from the Hub☆290Updated last week
- 🚀 Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash…☆268Updated 2 months ago
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆192Updated 3 months ago
- TransMLA: Multi-Head Latent Attention Is All You Need (NeurIPS 2025 Spotlight)☆372Updated last week
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆128Updated 10 months ago
- Training-free Post-training Efficient Sub-quadratic Complexity Attention. Implemented with OpenAI Triton.☆148Updated last week
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆320Updated last year
- VPTQ, A Flexible and Extreme low-bit quantization algorithm☆659Updated 5 months ago
- [ICLR2025 Spotlight] MagicPIG: LSH Sampling for Efficient LLM Generation☆238Updated 9 months ago
- ArcticTraining is a framework designed to simplify and accelerate the post-training process for large language models (LLMs)☆219Updated this week
- kernels, of the mega variety☆563Updated this week
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆168Updated last year
- ☆199Updated 4 months ago
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆241Updated last month
- Efficient triton implementation of Native Sparse Attention.☆226Updated 4 months ago
- A repository dedicated to evaluating the performance of quantizied LLaMA3 using various quantization methods..☆195Updated 8 months ago
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆412Updated this week
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆326Updated last week
- Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"☆246Updated 8 months ago