IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse
☆145Mar 14, 2026Updated 6 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:
- Memory-bounded compressed sparse attention via streaming top-k. Triton kernels for the DeepSeek-V4 lightning indexer. 32x regime extensio…☆26May 5, 2026Updated 4 months ago
- Offline optimization of your disaggregated Dynamo graph☆454Sep 18, 2026Updated 2 weeks ago
- a size profiler for cuda binary☆73Updated this week
- Autonomous GPU kernel optimization system driven by AI agents.☆31Mar 29, 2026Updated 6 months ago
- ☆104Feb 11, 2026Updated 7 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.
- Design hardware-friendly model architectures and migrate existing LLMs with minimal performance loss☆506Jul 14, 2026Updated 2 months ago
- Humming is a high-performance, lightweight, and highly flexible JIT (Just-In-Time) compiled GEMM kernel library specifically designed for…☆241Updated this week
- Official implementation of "Learning To Draft: Adaptive Speculative Decoding with Reinforcement Learning" (ICLR 2026)☆23Mar 1, 2026Updated 7 months ago
- Efficient GPU communication over multiple NICs.☆30Nov 20, 2025Updated 10 months ago
- DeepSeek-V3.2-Exp DSA Warmup Lightning Indexer training operator based on tilelang☆52Nov 19, 2025Updated 10 months ago
- Official implementation of the EMNLP23 paper: Outlier Suppression+: Accurate quantization of large language models by equivalent and opti…☆52Oct 21, 2023Updated 2 years ago
- Tile-Based Runtime for Ultra-Low-Latency LLM Inference☆1,831Sep 24, 2026Updated last week
- Recomputation-free, context-independent KV caching for large language models☆39Aug 12, 2026Updated last month
- ☆12Apr 25, 2024Updated 2 years 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.
- An hardware-aware Efficient Implementation for "Mixture-of-Depths Attention".☆280May 6, 2026Updated 4 months ago
- High Performance KV Cache Store for LLM☆58May 20, 2026Updated 4 months ago
- DICE: Detecting In-distribution Data Contamination with LLM's Internal State☆11Sep 21, 2024Updated 2 years ago
- ☆255Nov 19, 2025Updated 10 months ago
- Elastic Attention: Test-time Adaptive Sparsity Ratios for Efficient Transformers☆24May 26, 2026Updated 4 months ago
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆1,197Updated this week
- DeeperGEMM: crazy optimized version☆85May 5, 2025Updated last year
- Perplexity GPU Kernels☆607Nov 7, 2025Updated 10 months ago
- Production-ready MoE load balancing via real-time expert replication☆253Jul 17, 2026Updated 2 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- PegaFlow is a high-performance KV cache offloading solution for vLLM v1 on single-node multi-GPU setups.☆25Jan 7, 2026Updated 8 months ago
- High Performance LLM Inference Operator Library☆1,171Sep 7, 2026Updated 3 weeks ago
- Quantize transformers to any learned arbitrary 4-bit numeric format☆59Jul 2, 2026Updated 3 months ago
- ☆14Mar 21, 2020Updated 6 years ago
- An experimental communicating attention kernel based on DeepEP.☆34Jul 29, 2025Updated last year
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆862Mar 6, 2025Updated last year
- CODA: Rewriting Transformer Blocks as GEMM-Epilogue Programs☆254Updated this week
- A PyTorch native library for training speculative decoding models☆252Updated this week
- [EMNLP2026 Main] Official implementation of “Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding”.☆138Jul 25, 2026Updated 2 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- ☆34Feb 3, 2025Updated last year
- Adamas: Hadamard Sparse Attention for Efficient Long-context Inference☆15Updated this week
- An early research stage expert-parallel load balancer for MoE models based on linear programming.☆535Nov 19, 2025Updated 10 months ago
- Composable and Embeddable Communication Runtime for Distributed AI Services☆101Jun 5, 2026Updated 3 months ago
- Communication patterns for AI, built on top of NCCL device and host APIs☆66Updated this week
- [ICML 2025 Spotlight] ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference☆314May 1, 2025Updated last year
- Attention variant with per-channel multiplicative decay☆50Jun 3, 2026Updated 4 months ago