Algorithms for latent compaction
☆278Apr 22, 2026Updated 6 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☆349Mar 23, 2026Updated 7 months ago
- SR²AM: Efficient Agentic Reasoning Through Self-Regulated Simulative Planning☆21May 22, 2026Updated 5 months ago
- ☆21Oct 4, 2026Updated last month
- LLM KV cache compression made easy☆1,254Updated this week
- TriAttention — Efficient long reasoning with trigonometric KV cache compression. Enables OpenClaw local deployment on memory-constrained …☆870Aug 4, 2026Updated 3 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.
- [COLM-LLA 2026] The official implementation for paper "AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficien…☆24Aug 23, 2026Updated 2 months ago
- [ACL Findings 2026] Official Implementation of "FastKV: Decoupling of Context Reduction and KV Cache Compression for Prefill-Decoding Acc…☆34Apr 14, 2026Updated 7 months ago
- codebase for Coruscant: Co-Designing GPU Kernel and Sparse Tensor Core to Advocate Unstructured Sparsity in Efficient LLM Inference☆11Oct 17, 2025Updated last year
- Efficient Knowledge Injection in LLMs via Self-Distillation (TMLR)☆13Aug 5, 2025Updated last year
- Rust bindings for the [3FS USRBIO API](https://github.com/deepseek-ai/3FS/blob/main/src/lib/api/UsrbIo.md).☆11Nov 4, 2026Updated last week
- MinT-2M: Long-context training system for resident-prefix GRPO☆48Jul 24, 2026Updated 3 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)☆229Feb 11, 2026Updated 9 months ago
- ☆289Jun 6, 2025Updated last year
- CODA: Rewriting Transformer Blocks as GEMM-Epilogue Programs☆258Updated this week
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- FrontierSmith, a new system that uses AI to synthesize open-ended coding problems at scale☆84Oct 17, 2026Updated 3 weeks ago
- Code for the paper ReplaySSM: Cache SSM Inputs, Not State☆74Oct 13, 2026Updated last month
- ☆484Nov 25, 2025Updated 11 months ago
- ☆19May 27, 2026Updated 5 months ago
- Fused KL divergence from hidden states for knowledge distillation☆22Apr 28, 2026Updated 6 months ago
- Code for the paper *Attention Drift: What Speculative Decoding Models Learn*.☆33May 12, 2026Updated 6 months ago
- Triton kernels for dynamic causal short convolutions.☆35Jun 4, 2026Updated 5 months ago
- Accurate, fast FP4 KV-cache decoding through algorithm-system co-design.☆45Nov 9, 2026Updated last week
- KV cache compression via sparse coding☆18Oct 26, 2025Updated last year
- 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.
- Tiered optimizer state allocation for memory efficient MoE training. Cuts optimizer memory by 97.4%, outperforming AdamW/Muon/Lion while …☆14Sep 10, 2026Updated 2 months ago
- ☆19Jul 7, 2026Updated 4 months ago
- SpectralQuant: Calibrated Eigenbasis Rotation and Water-Filled Bit Allocation for KV-Cache Compression☆204May 15, 2026Updated 6 months ago
- Official codebase for AdaRank: Adaptive Rank Pruning for Enhanced Model Merging (ICLR 2026)☆20Jan 26, 2026Updated 9 months ago
- [TrimKV] Cache What Lasts: Token Retention for Memory-Bounded KV Cache in LLMs - [DBTrimKV] Make Each Token Count: Towards Improving Lo…☆23Jul 26, 2026Updated 3 months ago
- ☆31Sep 11, 2026Updated 2 months ago
- Official JAX implementation of End-to-End Test-Time Training for Long Context☆719Feb 15, 2026Updated 9 months ago
- Code for "Retaining Key Information under High Compression Rates: Query-Guided Compressor for LLMs" (ACL 2024)☆19Jun 12, 2024Updated 2 years ago
- ☆11May 24, 2024Updated 2 years 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.
- [NeurIPS 25] InfiniPot-V: Memory-Constrained KV Cache Compression for Streaming Video Understanding☆25Jan 25, 2026Updated 9 months ago
- ☆35Nov 11, 2025Updated last year
- ☆93Aug 19, 2026Updated 2 months ago
- Repository for TRACE: Capability-Targeted Agentic Training☆128Jul 12, 2026Updated 4 months ago
- Official implementation of Paper "System-Aware 4-Bit KV-Cache Quantization for Real-World LLM Serving"☆31Apr 17, 2026Updated 6 months ago
- LeapQuant: Efficient Linear Attention with Accurate Recurrent State Quantization☆54Updated this week
- Learning notes for understanding modern Machine Learning System.☆66Updated this week
Are these results useful?