Design hardware-friendly model architectures and migrate existing LLMs with minimal performance loss
☆501Jul 14, 2026Updated last month
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☆213Dec 4, 2025Updated 8 months ago
- ☆253Nov 19, 2025Updated 9 months ago
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆1,019Feb 5, 2026Updated 6 months ago
- ☆37Aug 7, 2025Updated last year
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆134Jun 24, 2025Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- 🚀 Efficient implementations for emerging model architectures☆5,665Updated this week
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆171Oct 13, 2025Updated 10 months ago
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆283Jul 6, 2025Updated last year
- Experiments on Multi-Head Latent Attention☆101Aug 19, 2024Updated 2 years ago
- [ICML 2025 Spotlight] ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference☆313May 1, 2025Updated last year
- A library for subgraph GNN based on pyg☆39Nov 28, 2024Updated last year
- IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse☆137Mar 14, 2026Updated 5 months ago
- DeeperGEMM: crazy optimized version☆85May 5, 2025Updated last year
- A sparse attention kernel supporting mix sparse patterns☆548Jan 18, 2026Updated 7 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Accelerating MoE with IO and Tile-aware Optimizations☆752Updated this week
- DeepSeek-V3.2-Exp DSA Warmup Lightning Indexer training operator based on tilelang☆52Nov 19, 2025Updated 9 months ago
- Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models☆343Feb 23, 2025Updated last year
- MoBA: Mixture of Block Attention for Long-Context LLMs☆2,173Apr 3, 2025Updated last year
- ☆138May 29, 2025Updated last year
- The repo for SHINE: A Scalable In-Context Hypernetwork for Mapping Context to LoRA in a Single Pass☆110Aug 18, 2026Updated last week
- FlashInfer: Kernel Library for LLM Serving☆6,290Updated this week
- [ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.☆1,042Feb 25, 2026Updated 6 months ago
- [ICLR2025 Spotlight] MagicPIG: LSH Sampling for Efficient LLM Generation☆256Dec 16, 2024Updated last year
- 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.
- Implementation of the sparse attention pattern proposed by the Deepseek team in their "Native Sparse Attention" paper☆811Aug 15, 2025Updated last year
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,226Apr 8, 2026Updated 4 months ago
- ☆121Feb 25, 2025Updated last year
- PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models(NeurIPS 2024 Spotlight)☆430Jun 30, 2025Updated last year
- Quantized Attention on GPU☆45Nov 22, 2024Updated last year
- ☆286Jun 6, 2025Updated last year
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆854Mar 6, 2025Updated last year
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training☆928Updated this week
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆52Jul 4, 2025Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆346Jul 2, 2024Updated 2 years ago
- Fast and Memory-Efficient Exact Attention (BF16/FP16/FP8/FP4) for Large Headdim, 1.5x~15x speedup over PyTorch SDPA.☆329Updated this week
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆539Feb 10, 2025Updated last year
- Efficient triton implementation of Native Sparse Attention.☆282May 23, 2025Updated last year
- Distributed MoE in a Single Kernel [NeurIPS '25]☆288May 5, 2026Updated 3 months ago
- 📰 Must-read papers on KV Cache Compression (constantly updating 🤗).☆737Aug 16, 2026Updated 2 weeks ago
- Source codes for paper "BlockFFN: Towards End-Side Acceleration-Friendly Mixture-of-Experts with Chunk-Level Activation Sparsity".☆19Jan 10, 2026Updated 7 months ago