Algorithms for latent compaction
☆270Apr 22, 2026Updated 5 months ago
Alternatives and similar repositories for compaction
Users that are interested in compaction are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Storing long contexts in tiny caches with self-study☆339Mar 23, 2026Updated 6 months ago
- SR²AM: Efficient Agentic Reasoning Through Self-Regulated Simulative Planning☆21May 22, 2026Updated 4 months ago
- LLM KV cache compression made easy☆1,224Updated this week
- [COLM-LLA 2026] The official implementation for paper "AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficien…☆23Aug 23, 2026Updated last month
- Triton kernels for dynamic causal short convolutions.☆30Jun 4, 2026Updated 3 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- TriAttention — Efficient long reasoning with trigonometric KV cache compression. Enables OpenClaw local deployment on memory-constrained …☆854Aug 4, 2026Updated last month
- [ACL Findings 2026] Official Implementation of "FastKV: Decoupling of Context Reduction and KV Cache Compression for Prefill-Decoding Acc…☆33Apr 14, 2026Updated 5 months ago
- ☆17Jun 15, 2026Updated 3 months ago
- ☆17May 27, 2026Updated 4 months ago
- Code for the paper *Attention Drift: What Speculative Decoding Models Learn*.☆32May 12, 2026Updated 4 months ago
- ☆288Jun 6, 2025Updated last year
- [TrimKV] Cache What Lasts: Token Retention for Memory-Bounded KV Cache in LLMs - [DBTrimKV] Make Each Token Count: Towards Improving Lo…☆21Jul 26, 2026Updated 2 months ago
- [NeurIPS'25 Oral] Query-agnostic KV cache eviction: 3–4× reduction in memory and 2× decrease in latency (Qwen3/2.5, Gemma3, LLaMA3)☆225Feb 11, 2026Updated 7 months ago
- FrontierSmith, a new system that uses AI to synthesize open-ended coding problems at scale☆80Updated this week
- 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.
- Fused KL divergence from hidden states for knowledge distillation☆22Apr 28, 2026Updated 5 months ago
- [NeurIPS 25] InfiniPot-V: Memory-Constrained KV Cache Compression for Streaming Video Understanding☆24Jan 25, 2026Updated 8 months ago
- ☆483Nov 25, 2025Updated 10 months ago
- A codebase for pretraining multi-billion-scale sparse GPTs.☆30Feb 9, 2026Updated 7 months ago
- CODA: Rewriting Transformer Blocks as GEMM-Epilogue Programs☆254Updated this week
- SpectralQuant: Calibrated Eigenbasis Rotation and Water-Filled Bit Allocation for KV-Cache Compression☆203May 15, 2026Updated 4 months ago
- Official JAX implementation of End-to-End Test-Time Training for Long Context☆708Feb 15, 2026Updated 7 months ago
- Official codebase for AdaRank: Adaptive Rank Pruning for Enhanced Model Merging (ICLR 2026)☆20Jan 26, 2026Updated 8 months ago
- ☆35Nov 11, 2025Updated 10 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- ☆30Sep 11, 2026Updated 3 weeks ago
- DiffusionBlocks: Block-wise Neural Network Training via Diffusion Interpretation☆319Feb 18, 2026Updated 7 months ago
- Official implementation of Paper "System-Aware 4-Bit KV-Cache Quantization for Real-World LLM Serving"☆30Apr 17, 2026Updated 5 months ago
- Pytorch code for paper QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models☆25Sep 27, 2023Updated 3 years ago
- ☆87Aug 19, 2026Updated last month
- Data generation and training repository for SERA: Soft-Verified Efficient Repository Agents.☆159May 25, 2026Updated 4 months ago
- ☆147Feb 4, 2026Updated 7 months ago
- [ICML 2025] CommVQ: Commutative Vector Quantization for KV Cache Compression☆27Sep 2, 2025Updated last year
- ☆42Mar 28, 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.
- The Official Implementation of Ada-KV [NeurIPS 2025]☆140Nov 26, 2025Updated 10 months ago
- AFPQ code implementation☆23Nov 6, 2023Updated 2 years ago
- GPU-optimized framework for training diffusion language models at any scale. The backend of Quokka, Super Data Learners, and OpenMoE 2 tr…☆343Nov 11, 2025Updated 10 months ago
- ☆27Jul 13, 2026Updated 2 months ago
- Fork of Flame repo for training of some new stuff in development☆20Aug 27, 2026Updated last month
- Code for the papers: “Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling” and “Adaptive Block-Scaled Data Types”☆204Apr 21, 2026Updated 5 months ago
- Fast low-bit matmul kernels in Triton☆487Updated this week