TransMLA: Multi-Head Latent Attention Is All You Need (NeurIPS 2025 Spotlight)
☆435Feb 28, 2026Updated 3 weeks ago
Alternatives and similar repositories for TransMLA
Users that are interested in TransMLA are comparing it to the libraries listed below
Sorting:
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆206Dec 4, 2025Updated 3 months ago
- Experiments on Multi-Head Latent Attention☆100Aug 19, 2024Updated last year
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆977Feb 5, 2026Updated last month
- 🚀 Efficient implementations of state-of-the-art linear attention models☆4,630Updated this week
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆164Oct 13, 2025Updated 5 months ago
- Quantized Attention on GPU☆44Nov 22, 2024Updated last year
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆273Jul 6, 2025Updated 8 months ago
- 🤖FFPA: Extend FlashAttention-2 with Split-D, ~O(1) SRAM complexity for large headdim, 1.8x~3x↑🎉 vs SDPA EA.☆253Feb 13, 2026Updated last month
- Transformers components but in Triton☆34May 9, 2025Updated 10 months ago
- ☆136May 29, 2025Updated 9 months ago
- MoBA: Mixture of Block Attention for Long-Context LLMs☆2,083Apr 3, 2025Updated 11 months ago
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆91Jul 17, 2025Updated 8 months ago
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆752Aug 6, 2025Updated 7 months ago
- ☆65Apr 26, 2025Updated 10 months ago
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆106Jun 28, 2025Updated 8 months ago
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆131Jun 24, 2025Updated 8 months ago
- High performance RMSNorm Implement by using SM Core Storage(Registers and Shared Memory)☆29Jan 22, 2026Updated 2 months ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆336Jul 2, 2024Updated last year
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆51Oct 18, 2024Updated last year
- PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models(NeurIPS 2024 Spotlight)☆415Jun 30, 2025Updated 8 months ago
- Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models☆341Feb 23, 2025Updated last year
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆818Mar 6, 2025Updated last year
- FlashMLA: Efficient Multi-head Latent Attention Kernels☆12,521Feb 6, 2026Updated last month
- ☆155Mar 4, 2025Updated last year
- Code for ICLR 2025 Paper "What is Wrong with Perplexity for Long-context Language Modeling?"☆110Oct 11, 2025Updated 5 months ago
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆242Jun 15, 2025Updated 9 months ago
- [ICML 2025 Spotlight] ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference☆286May 1, 2025Updated 10 months ago
- Fast low-bit matmul kernels in Triton☆438Feb 1, 2026Updated last month
- FlashInfer: Kernel Library for LLM Serving☆5,145Mar 15, 2026Updated last week
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,198Mar 9, 2026Updated last week
- ☆52May 19, 2025Updated 10 months ago
- LLM KV cache compression made easy☆971Mar 13, 2026Updated last week
- ☆139Aug 18, 2025Updated 7 months ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆1,041Sep 4, 2024Updated 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 11 months ago
- Efficient Triton Kernels for LLM Training☆6,216Updated this week
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆149May 10, 2025Updated 10 months ago
- ☆306Jul 10, 2025Updated 8 months ago
- Framework to reduce autotune overhead to zero for well known deployments.☆97Sep 19, 2025Updated 6 months ago