IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse
☆146Mar 14, 2026Updated 7 months ago
Alternatives and similar repositories for IndexCache
Users that are interested in IndexCache are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Efficient and unified implementations for TopK-based sparse attention☆41Jul 10, 2026Updated 3 months ago
- a size profiler for cuda binary☆74Oct 3, 2026Updated 2 weeks ago
- Communication patterns for AI, built on top of NCCL device and host APIs☆70Updated this week
- Autonomous GPU kernel optimization system driven by AI agents.☆32Mar 29, 2026Updated 6 months ago
- DeepSeek-V3.2-Exp DSA Warmup Lightning Indexer training operator based on tilelang☆52Nov 19, 2025Updated 11 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Offline optimization of your disaggregated Dynamo graph☆461Updated this week
- High-performance tokenization for inference☆14Updated this week
- Humming is a high-performance, lightweight, and highly flexible JIT (Just-In-Time) compiled GEMM kernel library specifically designed for…☆301Updated this week
- Memory-bounded compressed sparse attention via streaming top-k. Triton kernels for the DeepSeek-V4 lightning indexer. 32x regime extensio…☆27May 5, 2026Updated 5 months ago
- DeepSelect: TopK kernels for DeepSeek Sparse Attention (DSA) and Samplers☆495Sep 30, 2026Updated 3 weeks ago
- DeeperGEMM: crazy optimized version☆85May 5, 2025Updated last year
- Lightweight Benchmark Server for Agentic GPU Programming☆58Updated this week
- ☆116Aug 5, 2026Updated 2 months ago
- ☆27Jul 13, 2026Updated 3 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Tile-Based Runtime for Ultra-Low-Latency LLM Inference☆1,874Sep 24, 2026Updated 3 weeks ago
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling☆46Updated this week
- Design hardware-friendly model architectures and migrate existing LLMs with minimal performance loss☆513Updated this week
- ☆104Feb 11, 2026Updated 8 months ago
- ☆1,040Updated this week
- High Performance LLM Inference Operator Library☆1,184Sep 7, 2026Updated last month
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆865Mar 6, 2025Updated last year
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆1,233Updated this week
- [ICML 2025 Spotlight] ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference☆316May 1, 2025Updated last year
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- A high-performance, RDMA-native data-plane library for large-scale heterogeneous memory pools, developed by the Tencent Astral Network Te…☆33Aug 6, 2026Updated 2 months ago
- Perplexity GPU Kernels☆610Nov 7, 2025Updated 11 months ago
- MoonEP: A Perfectly Balanced Expert Parallelism Library via Dynamic Redundant Experts☆1,189Oct 12, 2026Updated last week
- Official implementation of "Learning To Draft: Adaptive Speculative Decoding with Reinforcement Learning" (ICLR 2026)☆23Mar 1, 2026Updated 7 months ago
- QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning☆204Sep 2, 2026Updated last month
- Open Source AI Accelerator Research Platform Standard / 开源推理研究平台☆1,901Updated this week
- Efficient GPU communication over multiple NICs.☆31Nov 20, 2025Updated 11 months ago
- A PyTorch native library for training speculative decoding models☆266Updated this week
- ☆255Nov 19, 2025Updated 11 months ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- [EMNLP2026 Main] Official implementation of “Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding”.☆140Jul 25, 2026Updated 2 months ago
- Flash-GMM, a memory-efficient GPU kernel that unlocks GMM soft clustering at billion-scale☆25Sep 30, 2026Updated 3 weeks ago
- FlashMemory DS-V4 Retriever: a lightweight retriever that sparsifies DeepSeek-V4 CSA KV-cache. Weights available on Hugging Face.☆112Jul 18, 2026Updated 3 months ago
- CODA: Rewriting Transformer Blocks as GEMM-Epilogue Programs☆256Oct 15, 2026Updated last week
- Production-ready MoE load balancing via real-time expert replication☆258Oct 15, 2026Updated last week
- An hardware-aware Efficient Implementation for "Mixture-of-Depths Attention".☆280May 6, 2026Updated 5 months ago
- Accepted to MLSys 2026☆97Apr 19, 2026Updated 6 months ago