IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse
☆141Mar 14, 2026Updated 5 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…☆25May 5, 2026Updated 4 months ago
- Offline optimization of your disaggregated Dynamo graph☆441Updated this week
- a size profiler for cuda binary☆71Jan 15, 2026Updated 7 months ago
- Autonomous GPU kernel optimization system driven by AI agents.☆31Mar 29, 2026Updated 5 months ago
- ☆102Feb 11, 2026Updated 7 months ago
- 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.
- Humming is a high-performance, lightweight, and highly flexible JIT (Just-In-Time) compiled GEMM kernel library specifically designed for…☆229Updated this week
- Design hardware-friendly model architectures and migrate existing LLMs with minimal performance loss☆502Jul 14, 2026Updated last month
- Official implementation of "Learning To Draft: Adaptive Speculative Decoding with Reinforcement Learning" (ICLR 2026)☆23Mar 1, 2026Updated 6 months ago
- Efficient GPU communication over multiple NICs.☆30Nov 20, 2025Updated 9 months ago
- DeepSeek-V3.2-Exp DSA Warmup Lightning Indexer training operator based on tilelang☆52Nov 19, 2025Updated 9 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☆1,759Aug 13, 2026Updated last month
- Recomputation-free, context-independent KV caching for large language models☆37Aug 12, 2026Updated last month
- ☆12Apr 25, 2024Updated 2 years ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- An hardware-aware Efficient Implementation for "Mixture-of-Depths Attention".☆277May 6, 2026Updated 4 months ago
- High Performance KV Cache Store for LLM☆59May 20, 2026Updated 3 months ago
- DICE: Detecting In-distribution Data Contamination with LLM's Internal State☆11Sep 21, 2024Updated last year
- ☆253Nov 19, 2025Updated 9 months ago
- Elastic Attention: Test-time Adaptive Sparsity Ratios for Efficient Transformers☆24May 26, 2026Updated 3 months ago
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆1,168Updated this week
- DeeperGEMM: crazy optimized version☆85May 5, 2025Updated last year
- Perplexity GPU Kernels☆608Nov 7, 2025Updated 10 months ago
- Production-ready MoE load balancing via real-time expert replication☆249Jul 17, 2026Updated last month
- 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.
- 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☆1,157Updated this week
- Quantize transformers to any learned arbitrary 4-bit numeric format☆59Jul 2, 2026Updated 2 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…☆858Mar 6, 2025Updated last year
- CODA: Rewriting Transformer Blocks as GEMM-Epilogue Programs☆250Updated this week
- A PyTorch native library for training speculative decoding models☆247Updated this week
- [EMNLP2026 Main] Official implementation of “Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding”.☆138Jul 25, 2026Updated last month
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- ☆34Feb 3, 2025Updated last year
- Adamas: Hadamard Sparse Attention for Efficient Long-context Inference☆15May 19, 2026Updated 3 months ago
- An early research stage expert-parallel load balancer for MoE models based on linear programming.☆530Nov 19, 2025Updated 9 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☆52Sep 3, 2026Updated last week
- Attention variant with per-channel multiplicative decay☆50Jun 3, 2026Updated 3 months ago
- A Triton JIT runtime and ffi provider in C++☆40Updated this week