[ACL 2024] RelayAttention for Efficient Large Language Model Serving with Long System Prompts
☆39Feb 29, 2024Updated 2 years ago
Alternatives and similar repositories for vllm-ra
Users that are interested in vllm-ra are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆89Apr 18, 2025Updated last year
- ☆135Nov 11, 2024Updated last year
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆154Dec 4, 2024Updated last year
- This is a fork of SGLang for hip-attention integration. Please refer to hip-attention for detail.☆18Mar 31, 2026Updated 3 months ago
- This is the official repo for the paper "Accelerating Parallel Sampling of Diffusion Models" Tang et al. ICML 2024 https://openreview.net…☆16Jul 19, 2024Updated 2 years ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- [ICLR 2024] CLEX: Continuous Length Extrapolation for Large Language Models☆78Mar 12, 2024Updated 2 years ago
- ☆13Jan 7, 2025Updated last year
- Injecting Adrenaline into LLM Serving: Boosting Resource Utilization and Throughput via Attention Disaggregation☆42Jul 13, 2026Updated last week
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆222Sep 21, 2024Updated last year
- Code of "To The Point: Correspondence-driven monocular 3D category reconstruction (TTP)" Neurips 2021☆11Jan 24, 2022Updated 4 years ago
- ☆156Mar 4, 2025Updated last year
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training☆223Aug 19, 2024Updated last year
- ☆96Dec 6, 2024Updated last year
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆418Nov 20, 2025Updated 8 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Research prototype of PRISM — a cost-efficient multi-LLM serving system with flexible time- and space-based GPU sharing.☆71Mar 17, 2026Updated 4 months ago
- Awesome Quantization Paper lists with Codes☆10Feb 24, 2021Updated 5 years ago
- KV cache compression for high-throughput LLM inference☆158Feb 5, 2025Updated last year
- ☆11Apr 5, 2021Updated 5 years ago
- ☆24Dec 11, 2024Updated last year
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆539Feb 10, 2025Updated last year
- The official implementation of the EMNLP 2023 paper LLM-FP4☆224Dec 15, 2023Updated 2 years ago
- Whisper in TensorRT-LLM☆17Sep 21, 2023Updated 2 years ago
- ☆11Apr 14, 2022Updated 4 years ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- A low-latency & high-throughput serving engine for LLMs☆511Jan 8, 2026Updated 6 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆170Oct 13, 2025Updated 9 months ago
- ☆65Apr 26, 2025Updated last year
- Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic speed up with better task performance…☆157Apr 7, 2025Updated last year
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆183Jul 12, 2024Updated 2 years ago
- PyTorch code for our paper "Progressive Binarization with Semi-Structured Pruning for LLMs"☆13Jul 11, 2026Updated last week
- A curated list of recent papers on efficient video attention for video diffusion models, including sparsification, quantization, and cach…☆61Oct 27, 2025Updated 8 months ago
- ☢️ TensorRT 2023复赛——基于TensorRT-LLM的Llama模型推断加速优化☆54Oct 20, 2023Updated 2 years ago
- ☆26Mar 31, 2026Updated 3 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Compare different hardware platforms via the Roofline Model for LLM inference tasks.☆123Mar 13, 2024Updated 2 years ago
- Deep Variational Information Bottleneck (DVIB) in PyTorch.☆10Apr 25, 2020Updated 6 years ago
- ☆24Jul 8, 2024Updated 2 years ago
- A throughput-oriented high-performance serving framework for LLMs☆968Mar 29, 2026Updated 3 months ago
- Multi-Layer Key-Value sharing experiments on Pythia models☆34Jun 14, 2024Updated 2 years ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆64Jun 5, 2024Updated 2 years ago
- ☆54Feb 19, 2024Updated 2 years ago