LLM KV Cache compression - K+V dual compression, 73-99% VRAM savings, zero accuracy loss
☆49Mar 30, 2026Updated 2 weeks ago
Alternatives and similar repositories for polarquant-kv
Users that are interested in polarquant-kv are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆13Aug 30, 2021Updated 4 years ago
- Scala implementation of Aho-Corasick algorithm☆15May 6, 2022Updated 3 years ago
- Fully open reproduction of DeepSeek-R1☆11Mar 24, 2025Updated last year
- 集中管理所有的prompt。☆14Nov 27, 2024Updated last year
- Official Codebase for "Aligning Diffusion Behaviors with Q-functions for Efficient Continuous Control" (NeurIPS 2024)☆15Oct 29, 2024Updated last year
- Wordpress hosting with auto-scaling - Free Trial • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- GEMV implementation with CUTLASS☆21Aug 21, 2025Updated 7 months ago
- Zeta implementation of a reusable and plug in and play feedforward from the paper "Exponentially Faster Language Modeling"☆16Nov 11, 2024Updated last year
- ☆25Jul 3, 2018Updated 7 years ago
- 🖖 图谱式笔记系统，旨在提高个人笔记的使用率！☆12Jan 17, 2021Updated 5 years ago
- The source code for my bachelor's thesis "Abstractive Summarization of Meetings"☆21May 21, 2021Updated 4 years ago
- A Python-based tool that uses Azure OpenAI to process and summarize meeting transcripts from platforms like Microsoft Teams and Skype. Si…☆16Jan 29, 2025Updated last year
- 5 Stage Pipelined RISC V Processor Design for RV32I Instruction Set☆10Sep 15, 2022Updated 3 years ago
- ☆34Feb 9, 2026Updated 2 months ago
- ☆18Jan 25, 2026Updated 2 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- A simple implementation of ReasonGenRM.☆19Apr 21, 2025Updated 11 months ago
- A prototype repo for hybrid training of pipeline parallel and distributed data parallel with comments on core code snippets. Feel free to…☆58Jul 4, 2023Updated 2 years ago
- MeloTTS demo on Axera☆12Nov 18, 2025Updated 5 months ago
- opensource NPU for LLM inference (this run gpt2)☆63Feb 16, 2026Updated 2 months ago
- fetch-skill☆111Mar 22, 2026Updated 3 weeks ago
- Reproduced the DFT method without using Verl. https://arxiv.org/abs/2508.05629☆22Oct 14, 2025Updated 6 months ago
- this repo is mnbvc text quality classification using fastText☆16Oct 2, 2023Updated 2 years ago
- https://openjdk.org/projects/jdk-updates☆36Apr 9, 2026Updated last week
- java implementation of Bert Tokenizer, support output onnx tensor for onnx model inference☆13Sep 4, 2023Updated 2 years ago
- 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.
- This is a detailed code demo on how to conduct Full-Param Supervised Fine-tuning (SFT) and DPO (Direct Preference Optimization)☆19Jan 9, 2025Updated last year
- ☆25Mar 8, 2026Updated last month
- The implementation of Text Classification with Negative Supervision (ACL, 2020)☆10Oct 8, 2020Updated 5 years ago
- [ICML 2025] Official code of "AlphaDPO: Adaptive Reward Margin for Direct Preference Optimization"☆31Jan 10, 2026Updated 3 months ago
- ☆33Oct 13, 2025Updated 6 months ago
- 使用Sentencepiece对中文语料进行分词☆13Nov 30, 2023Updated 2 years ago
- FlashTile is a CUDA Tile IR compiler that is compatible with NVIDIA's tileiras, targeting SM70 through SM121 NVIDIA GPUs.☆60Feb 6, 2026Updated 2 months ago
- 在您的机器上本地离线运行 AI 模型☆11May 8, 2025Updated 11 months ago
- 👂 Typing is slow, talk to me. The project name means ' i am tired ' in Chinese (我累了). This is a AI efficiency assistant, complete your d…☆16Jun 8, 2024Updated last year
- Wordpress hosting with auto-scaling - Free Trial • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Qwen-WisdomVast is a large model trained on 1 million high-quality Chinese multi-turn SFT data, 200,000 English multi-turn SFT data, and …☆18Apr 12, 2024Updated 2 years ago
- ☆17Jan 31, 2025Updated last year
- Code for "Translatotron-V(ison): An End-to-End Model for In-Image Machine Translation" (Findings of ACL 2024)☆16Jul 4, 2024Updated last year
- gpt-o1 like chain of thoughts with local LLMs in R☆31Oct 15, 2024Updated last year
- A RISC-V processor simulator☆29Jul 12, 2022Updated 3 years ago
- [EMNLP 2024] Source code for the paper "Learning Planning-based Reasoning with Trajectory Collection and Process Rewards Synthesizing".☆83Jan 14, 2025Updated last year
- ☆71Oct 30, 2025Updated 5 months ago