sgl-project / sgl-flash-attnLinks
Fast and memory-efficient exact attention
☆15Updated this week
Alternatives and similar repositories for sgl-flash-attn
Users that are interested in sgl-flash-attn are comparing it to the libraries listed below
Sorting:
- DeeperGEMM: crazy optimized version☆74Updated 8 months ago
- Efficient Long-context Language Model Training by Core Attention Disaggregation☆79Updated 2 weeks ago
- ☆39Updated 5 months ago
- ☆52Updated 7 months ago
- ☆65Updated 8 months ago
- DeepSeek-V3.2-Exp DSA Warmup Lightning Indexer training operator based on tilelang☆41Updated last month
- A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters☆54Updated last year
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆136Updated last year
- An experimental communicating attention kernel based on DeepEP.☆35Updated 5 months ago
- ☆84Updated 9 months ago
- Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding☆79Updated last month
- Estimate MFU for DeepSeekV3☆26Updated last year
- Debug print operator for cudagraph debugging☆14Updated last year
- Quantized Attention on GPU☆44Updated last year
- 16-fold memory access reduction with nearly no loss☆109Updated 9 months ago
- [Archived] For the latest updates and community contribution, please visit: https://github.com/Ascend/TransferQueue or https://gitcode.co…☆13Updated this week
- DLSlime: Flexible & Efficient Heterogeneous Transfer Toolkit☆91Updated this week
- Efficient Compute-Communication Overlap for Distributed LLM Inference☆68Updated 2 months ago
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆51Updated 6 months ago
- Kernel Library Wheel for SGLang☆17Updated this week
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆52Updated 5 months ago
- 🔥 LLM-powered GPU kernel synthesis: Train models to convert PyTorch ops into optimized Triton kernels via SFT+RL. Multi-turn compilation…☆112Updated 2 months ago
- Stateful LLM Serving☆94Updated 10 months ago
- ☆96Updated 9 months ago
- ☆41Updated 3 months ago
- DeepXTrace is a lightweight tool for precisely diagnosing slow ranks in DeepEP-based environments.☆86Updated 3 weeks ago
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆67Updated last year
- A simple calculation for LLM MFU.☆63Updated 4 months ago
- Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.☆113Updated 2 weeks ago
- Nex Venus Communication Library☆70Updated 2 months ago