Infini-AI-Lab / vortex_torchLinks
Vortex: A Flexible and Efficient Sparse Attention Framework
☆43Updated 3 weeks ago
Alternatives and similar repositories for vortex_torch
Users that are interested in vortex_torch are comparing it to the libraries listed below
Sorting:
- Quantized Attention on GPU☆44Updated last year
- ☆133Updated 6 months ago
- Odysseus: Playground of LLM Sequence Parallelism☆78Updated last year
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆51Updated 5 months ago
- ☆115Updated 7 months ago
- ☆125Updated 4 months ago
- Transformers components but in Triton☆34Updated 7 months ago
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆52Updated last year
- ☆52Updated 7 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆135Updated last year
- 16-fold memory access reduction with nearly no loss☆109Updated 8 months ago
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆49Updated 4 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆159Updated 2 months ago
- ☆83Updated 11 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆172Updated last year
- Efficient Long-context Language Model Training by Core Attention Disaggregation☆55Updated this week
- Boosting 4-bit inference kernels with 2:4 Sparsity☆89Updated last year
- A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters☆52Updated last year
- [ACL 2025] Squeezed Attention: Accelerating Long Prompt LLM Inference☆54Updated last year
- 🔥 LLM-powered GPU kernel synthesis: Train models to convert PyTorch ops into optimized Triton kernels via SFT+RL. Multi-turn compilation…☆107Updated last month
- The evaluation framework for training-free sparse attention in LLMs☆106Updated 2 months ago
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆126Updated 5 months ago
- Code for the paper “Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling”☆78Updated this week
- [ICML 2025] SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity☆64Updated 5 months ago
- ☆156Updated 10 months ago
- DeeperGEMM: crazy optimized version☆73Updated 7 months ago
- [ACL 2024] RelayAttention for Efficient Large Language Model Serving with Long System Prompts☆40Updated last year
- ☆65Updated 7 months ago
- ☆39Updated 4 months ago
- Framework to reduce autotune overhead to zero for well known deployments.☆90Updated 3 months ago