sgl-project / sgl-flash-attnLinks
Fast and memory-efficient exact attention
☆14Updated 2 weeks ago
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:
- ☆51Updated 6 months ago
- ☆39Updated 4 months ago
- DeepSeek-V3.2-Exp DSA Warmup Lightning Indexer training operator based on tilelang☆34Updated 2 weeks ago
- Debug print operator for cudagraph debugging☆14Updated last year
- DeeperGEMM: crazy optimized version☆73Updated 7 months ago
- ☆65Updated 7 months ago
- An experimental communicating attention kernel based on DeepEP.☆35Updated 4 months ago
- A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters☆52Updated last year
- Estimate MFU for DeepSeekV3☆26Updated 11 months ago
- Efficient Compute-Communication Overlap for Distributed LLM Inference☆63Updated last month
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆49Updated 4 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆133Updated last year
- DeepXTrace is a lightweight tool for precisely diagnosing slow ranks in DeepEP-based environments.☆70Updated last week
- Quantized Attention on GPU☆44Updated last year
- 16-fold memory access reduction with nearly no loss☆108Updated 8 months ago
- Kernel Library Wheel for SGLang☆16Updated this week
- ☆82Updated 7 months ago
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆51Updated 5 months ago
- ☆31Updated 5 months ago
- DLSlime: Flexible & Efficient Heterogeneous Transfer Toolkit☆82Updated this week
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆65Updated last year
- Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.☆104Updated 2 months ago
- Nex Venus Communication Library☆61Updated 3 weeks ago
- 🔥 LLM-powered GPU kernel synthesis: Train models to convert PyTorch ops into optimized Triton kernels via SFT+RL. Multi-turn compilation…☆103Updated 3 weeks ago
- Vortex: A Flexible and Efficient Sparse Attention Framework☆41Updated last week
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆200Updated last year
- Stateful LLM Serving☆89Updated 8 months ago
- ☆60Updated 2 weeks ago
- A simple calculation for LLM MFU.☆50Updated 2 months ago
- ☆13Updated 11 months ago