Design hardware-friendly model architectures and migrate existing LLMs with minimal performance loss
☆472May 18, 2026Updated this week
Alternatives and similar repositories for TransArch
Users that are interested in TransArch are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆212Dec 4, 2025Updated 5 months ago
- The repo for SHINE: A Scalable In-Context Hypernetwork for Mapping Context to LoRA in a Single Pass☆68May 1, 2026Updated 2 weeks ago
- Experiments on Multi-Head Latent Attention☆101Aug 19, 2024Updated last year
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆1,000Feb 5, 2026Updated 3 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆168Oct 13, 2025Updated 7 months 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.
- 🚀 Efficient implementations for emerging model architectures☆5,116Updated this week
- Quantized Attention on GPU☆44Nov 22, 2024Updated last year
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆277Jul 6, 2025Updated 10 months ago
- Implementation of the sparse attention pattern proposed by the Deepseek team in their "Native Sparse Attention" paper☆805Aug 15, 2025Updated 9 months ago
- MoBA: Mixture of Block Attention for Long-Context LLMs☆2,117Apr 3, 2025Updated last year
- Transformers components but in Triton☆34May 9, 2025Updated last year
- ☆138May 29, 2025Updated 11 months ago
- 🤖FFPA: Extends FlashAttention-2 via Split-D for large headdims, 1.5x~3×↑🎉 vs SDPA, up to 430T🎉 on H200.☆299Updated this week
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆92Jul 17, 2025Updated 10 months ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆764Aug 6, 2025Updated 9 months ago
- ☆66Apr 26, 2025Updated last year
- PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models(NeurIPS 2024 Spotlight)☆425Jun 30, 2025Updated 10 months ago
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆133Jun 24, 2025Updated 10 months ago
- High performance RMSNorm Implement by using SM Core Storage(Registers and Shared Memory)☆30Jan 22, 2026Updated 3 months ago
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆109Jun 28, 2025Updated 10 months ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆339Jul 2, 2024Updated last year
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆51Oct 18, 2024Updated last year
- Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models☆344Feb 23, 2025Updated last year
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- FlashMLA: Efficient Multi-head Latent Attention Kernels☆12,651Apr 30, 2026Updated 3 weeks ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆838Mar 6, 2025Updated last year
- Code for ICLR 2025 Paper "What is Wrong with Perplexity for Long-context Language Modeling?"☆113Oct 11, 2025Updated 7 months ago
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,212Apr 8, 2026Updated last month
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆252Jun 15, 2025Updated 11 months ago
- Efficient triton implementation of Native Sparse Attention.☆277May 23, 2025Updated 11 months ago
- ☆248Nov 19, 2025Updated 6 months ago
- Fast low-bit matmul kernels in Triton☆454Updated this week
- Efficient Triton Kernels for LLM Training☆6,365Updated this week
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- ☆52May 19, 2025Updated last year
- [ICML 2025 Spotlight] ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference☆299May 1, 2025Updated last year
- ☆143Aug 18, 2025Updated 9 months ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆1,076Sep 4, 2024Updated last year
- FlashInfer: Kernel Library for LLM Serving☆5,621Updated this week
- ☆157Mar 4, 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…☆156Apr 7, 2025Updated last year