FlashMemory DS-V4 Retriever: a lightweight retriever that sparsifies DeepSeek-V4 CSA KV-cache. Weights available on Hugging Face.
☆111Jul 18, 2026Updated 3 months ago
Alternatives and similar repositories for FlashMemory-Deepseek-V4
Users that are interested in FlashMemory-Deepseek-V4 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…☆27May 5, 2026Updated 6 months ago
- Official code for HiLS-Attention☆153Aug 13, 2026Updated 2 months ago
- ☆437Oct 31, 2026Updated last week
- Official Repo for paper "VLCache: Computing 2% Vision Tokens and Reusing 98% for Vision-Language Inference"☆16Mar 28, 2026Updated 7 months ago
- DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention☆25May 25, 2026Updated 5 months ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- ☆11Oct 29, 2026Updated 2 weeks ago
- Kwai Summary Attention☆63Updated this week
- A high-performance, RDMA-native data-plane library for large-scale heterogeneous memory pools, developed by the Tencent Astral Network Te…☆35Aug 6, 2026Updated 3 months ago
- [ICLR 2026] LookaheadKV: Fast and Accurate KV Cache Eviction by Glimpsing into the Future without Generation☆14Mar 16, 2026Updated 7 months ago
- Pixels, Patterns, but no Poetry: To See the World like Humans☆18Aug 11, 2025Updated last year
- ☆10May 22, 2024Updated 2 years ago
- GenAI evaluation framework, optimized for 100x lower cost 🚀.☆48Sep 28, 2026Updated last month
- IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse☆147Mar 14, 2026Updated 7 months ago
- ☆12Nov 21, 2025Updated 11 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.
- A lightweight CuTe-based CUDA kernel for DuoAttention, optimized for large language model inference.☆12Dec 25, 2025Updated 10 months ago
- Control Logic Synthesis: Drawing the Rest of the OWL☆13Jun 17, 2024Updated 2 years ago
- [ECCV 2026] Dotting the Eye: An Intent-Driven Image Retouching Agent for Visual Focus Enhancement☆17Sep 14, 2026Updated last month
- Zhuofan Lin and Shiju Lin, "GPU-Accelerated Efficient Transduction for Logic Optimization", Design, Automation & Test in Europe Conferenc…☆14Sep 19, 2026Updated last month
- Mini-SGLang is a mini version of SGLang project ().☆13Sep 24, 2025Updated last year
- "GraphArena: Evaluating and Exploring Large Language Models on Graph Computation" in ICLR 2025☆34Mar 2, 2025Updated last year
- ☆27Jul 13, 2026Updated 3 months ago
- [DAC2024] Explainable Fuzzy Neural Network with Multi-Fidelity Reinforcement Learning for Micro-Architecture Design Space Exploration☆10Jul 21, 2026Updated 3 months ago
- ☆12Updated this week
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- ☆37Updated this week
- Sparse Decoupled Attention for Efficient Long-Context LLM Inference☆74Jun 4, 2026Updated 5 months ago
- CuteDSL Swizzle Visualize Tool☆14Feb 22, 2026Updated 8 months ago
- Reliable Sandbox for Agent, with agent-aware Checkpoint and Restore ability.☆15Aug 31, 2026Updated 2 months ago
- End-to-End Mixed Precision Neural Network Co-Exploration Framework for Edge AI☆12Sep 21, 2026Updated last month
- A sparse-first inference engine (SparseEngine).☆108Updated this week
- JetSpec++/JetSpec: Causal Parallel (Tree) Drafting with Self Refinement☆257Updated this week
- BlitzScale Router - Distributed LLM Inference Router (Rust)☆18May 25, 2026Updated 5 months ago
- MetaLadder: Ascending Mathematical Solution Quality via Analogical-Problem Reasoning Transfer (EMNLP 2025)☆12Apr 18, 2025Updated last year
- 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.
- [ECCV 2026] GeoWorld: Providing Full-frame Geometry Features to Facilitate 3D Scene Generation☆20Sep 7, 2026Updated 2 months ago
- ☆21Oct 24, 2026Updated 2 weeks ago
- An official implementation of "Joint Inference of Diffusion and Structure in Partially Observed Social Networks Using Coupled Matrix Fact…☆10Sep 26, 2023Updated 3 years ago
- ☆13May 21, 2026Updated 5 months ago
- Extrapolating RLVR to General Domains without Verifiers☆205Aug 12, 2025Updated last year
- ☆43Jun 8, 2026Updated 5 months ago
- A unified, torch-native training framework for MTP and block-parallel speculative decoding.☆287Jul 31, 2026Updated 3 months ago
Are these results useful?