Softened ROSA QKV Operators for Training Next-Generation LLM Models
☆38Apr 7, 2026Updated last month
Alternatives and similar repositories for rosa_soft
Users that are interested in rosa_soft are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ROSA-Tuning☆73Feb 4, 2026Updated 3 months ago
- ☆14May 11, 2025Updated last year
- Accepted to ICLR 2025. MetaMetrics is a calibrated meta-metric designed to evaluate generation tasks across different modalities aligned …☆15Dec 30, 2024Updated last year
- ☆14May 15, 2023Updated 3 years ago
- State tuning tunes the state☆35Feb 12, 2025Updated last year
- 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.
- Sources and examples for ASPLOS20 paper☆14Jul 21, 2020Updated 5 years ago
- Model Doctor: A Simple Gradient Aggregation Strategy for Diagnosing and Treating CNN Classifiers [https://arxiv.org/pdf/2112.04934.pdf]☆15May 13, 2023Updated 3 years ago
- Official PyTorch implementation of paper "Schema Inference for Interpretable Image Classification" (ICLR 2023)☆15Apr 6, 2023Updated 3 years ago
- RWKV-7 7.2B fp16 15000+ tps decoding @ single 5090☆110Updated this week
- This project is established for real-time training of the RWKV model.☆49May 17, 2024Updated 2 years ago
- Modified Beam Search with periodical restart☆12Sep 12, 2024Updated last year
- A scalable distributed graph partitioner. Ongoing research.☆15Apr 23, 2017Updated 9 years ago
- ☆83Updated this week
- Streaming Graph Server with partitioning☆15Aug 17, 2023Updated 2 years 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.
- [ICLR2026] The official repository for the CodeGym project: "Generalizable End-to-End Tool-Use RL with Synthetic CodeGym"☆31Oct 14, 2025Updated 7 months ago
- This is a fork of SGLang for hip-attention integration. Please refer to hip-attention for detail.☆18Mar 31, 2026Updated last month
- Fast modular code to create and train cutting edge LLMs☆67May 16, 2024Updated 2 years ago
- The source code of "A Comprehensive Survey and Experimental Study of Subgraph Matching: Trends, Unbiasedness, and Interaction"☆17Sep 6, 2024Updated last year
- pure go for rwkv☆18Dec 31, 2023Updated 2 years ago
- The benchmark proposed in paper: GraphInstruct: Empowering Large Language Models with Graph Understanding and Reasoning Capability☆25Aug 12, 2025Updated 9 months ago
- Yet another frontend for LLM, written using .NET and WinUI 3☆11Sep 14, 2025Updated 8 months ago
- RWKV is a RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best …☆10Nov 3, 2023Updated 2 years ago
- The official implementation of Bi-Mamba☆16Oct 22, 2025Updated 7 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 11, 2023Updated 2 years ago
- Table extraction library☆31Mar 9, 2025Updated last year
- ROSA+: RWKV's ROSA implementation with fallback statistical predictor☆35Oct 13, 2025Updated 7 months ago
- 基于Funasr的[实时]AI语音助手☆24Dec 18, 2025Updated 5 months ago
- The repo for SHINE: A Scalable In-Context Hypernetwork for Mapping Context to LoRA in a Single Pass☆68May 1, 2026Updated 3 weeks ago
- Zeta implementation of a reusable and plug in and play feedforward from the paper "Exponentially Faster Language Modeling"☆16Nov 11, 2024Updated last year
- Code for paper: Long cOntext aliGnment via efficient preference Optimization☆24Oct 10, 2025Updated 7 months ago
- A sleek, customizable interface for managing LLMs with responsive design and easy agent personalization.☆17Aug 30, 2024Updated last year
- The official implementation of the paper "MLP Memory: A Retriever-Pretrained Memory for Large Language Models". (ICLR 2026)☆65Jan 28, 2026Updated 3 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.
- Prose Markup Language☆10Mar 31, 2023Updated 3 years ago
- Re:Phiedit 指南：通过重构 RPE 说明书结构，优化阅读体验，减少 RPE 说明书的理解成本☆17Apr 16, 2023Updated 3 years ago
- ☆26Apr 20, 2023Updated 3 years ago
- SGLang kernel library for NPU☆137Updated this week
- a.k.a autoMBW-V2☆10Sep 6, 2024Updated last year
- ☆74Mar 23, 2026Updated 2 months ago
- pytorch implementation of grok☆11Updated this week