π₯ [ICML'26] ParisKV: Fast and Drift-Robust KV-Cache Retrieval for Long-Context LLMs
β30Jun 29, 2026Updated last month
Alternatives and similar repositories for ParisKV
Users that are interested in ParisKV are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [SIGMOD 2025] PQCache: Product Quantization-based KVCache for Long Context LLM Inferenceβ91Dec 7, 2025Updated 7 months ago
- [VLDB 26, NeurIPS 25] Scalable long-context LLM decoding that leverages sparsityβby treating the KV cache as a vector storage system.β149Updated this week
- Adamas: Hadamard Sparse Attention for Efficient Long-context Inferenceβ15May 19, 2026Updated 2 months ago
- Segmented Code Adjustment Quantization (SAQ)β26Sep 22, 2025Updated 10 months ago
- [ICML 2025] RocketKV: Accelerating Long-Context LLM Inference via Two-Stage KV Cache Compressionβ50Aug 7, 2025Updated 11 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer β’ AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Official github repo for "Fractional Reasoning via Latent Steering Vectors Improves Inference Time Compute"β17Jun 30, 2025Updated last year
- The official implementation of NOSAβ20Jun 11, 2026Updated last month
- Implementation for IceCache: Memory-Efficient KV-cache Management for Long-Sequence LLMs (ICLR 2026).β20Jun 9, 2026Updated last month
- Muon in Int8 Precision Made Possibleβ20Jun 18, 2026Updated last month
- Algorithm-System Co-design: accurate and efficient 2-bit KV cache quantization for LLM Inference.β19May 20, 2026Updated 2 months ago
- β16Jul 29, 2025Updated last year
- TurboQuant reference implementation β KV cache compression with engineering insights (ICLR 2026 paper reproduction)β17Mar 28, 2026Updated 4 months ago
- Code, Data and Model for Paper "Learning from Peers in Reasoning Models"β26May 13, 2025Updated last year
- Query-Adaptive Vector Searchβ77Mar 19, 2026Updated 4 months ago
- Deploy on Railway without the complexity - Free Credits Offer β’ AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Official implementation of "Learning To Draft: Adaptive Speculative Decoding with Reinforcement Learning" (ICLR 2026)β21Mar 1, 2026Updated 5 months ago
- High-Performance Embeddable Vector Database with Document Storage, Hybrid Search, and Filteringβ86Jun 4, 2026Updated 2 months ago
- The Official Implementation of Ada-KV [NeurIPS 2025]β139Nov 26, 2025Updated 8 months ago
- rabitq rust implementationβ11May 14, 2026Updated 2 months ago
- Query-Aware LSH for Approximate NNS (PVLDB 2015 and VLDBJ 2017)β28Jul 9, 2021Updated 5 years ago
- A new query hardness measure for graph-based ANN indexes. Build unbiased workloads with this hardness to see the actual performance of yoβ¦β22May 6, 2026Updated 2 months ago
- Public repository for CleANN, an efficient fully-dynamic approximate nearest neighbor search indexβ16Sep 18, 2025Updated 10 months ago
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scalingβ34Updated this week
- A cross-modal vector index with fast construction on heterogeneous CPU-GPU environment. Published on DaMoN@SIGMOD 2025.β16Jul 16, 2025Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer β’ AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- [ICML2025] Official code for "Reinforced Lifelong Editing for Language Models"β22Feb 23, 2025Updated last year
- Repository for SIEVE: Effective Filtered Vector Search with Collection of Indexes VLDB '25 submissionβ17Jul 30, 2025Updated last year
- FA4-based Relative Attention Kernel developed by TML and Colfaxβ17Jul 17, 2026Updated 2 weeks ago
- [NeurIPS'25 Spotlight] Adaptive Attention Sparsity with Hierarchical Top-p Pruningβ105Jul 8, 2026Updated 3 weeks ago
- Handwritten GEMM using Intel AMX (Advanced Matrix Extension)β17Jan 11, 2025Updated last year
- [ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafterβ176Feb 27, 2026Updated 5 months ago
- β37Aug 7, 2025Updated 11 months ago
- Triton kernels and PyTorch ops for Block Attention Residuals (AttnRes)β86May 29, 2026Updated 2 months ago
- Debug print operator for cudagraph debuggingβ18Aug 2, 2024Updated 2 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer β’ AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- β‘ Super fast clustering for high-dimensional vectors on CPUs (x86, ARM) and GPUs β for Python and C++. 100x faster clustering of vector eβ¦β70Updated this week
- δΈΊHSNWζΊη ε δΈδΊθ―¦η»η注ιβ20Oct 26, 2022Updated 3 years ago
- HiCache: Hermite Polynomial-based Feature Cache for diffusion inferenceβ15Updated this week
- A low-latency, billion-scale, and updatable graph-based vector store on SSD.β145Jul 19, 2026Updated 2 weeks ago
- Dynamic Context Selection for Efficient Long-Context LLMsβ63May 20, 2025Updated last year
- β40Jun 18, 2025Updated last year
- [KDD 2026] Chem-R: Learning to Reason as a Chemistβ30Oct 19, 2025Updated 9 months ago