@jerryjliu0: If I only went off X posts, I'd think Ramp was an AI lab
Summary
Ramp Labs open-sourced PorTAL, a framework for shared task representations and cross-model LoRA adaptation, supporting hybrid attention models and multimodal systems including Gemma 4, Mistral 7B, and Inkling.
View Cached Full Text
Cached at: 07/28/26, 06:36 AM
If I only went off X posts, I’d think Ramp was an AI lab
Ramp Labs (@RampLabs): We’re open-sourcing PorTAL, our framework for shared task representations and cross model LoRA adaptation.
It now spans from hybrid attention models to multimodal systems including Gemma 4 E2B, Mistral 7B & @thinkymachines’ Inkling.
Code: ramp-public/portallib Models:
Similar Articles
@jerryjliu0: A full tour through RAG, document context, and AI agents - from 2023 to 2026 @hexapode gave a comprehensive 90-min work…
Comprehensive workshop slides tracing the evolution of RAG, document context, and AI agents from 2023 to 2026, covering pain points, reranking, agent loops, and document parsing challenges.
@Redpoint: Why did a spend management platform start its own AI research lab? @karimatiyeh describes @RampLabs as a “collection of…
Ramp, a spend management platform, launched its own AI research lab called Ramp Labs a year ago. The lab has worked on projects like a production-focused coding benchmark 'Ramp SWE-Bench', integrating Claude Code into RollerCoaster Tycoon, and a mechanistic interpretability playground.
@didier_lopes: Incredible how Z. ai literally has their RL infrastructure open source. The entire OPD post-training of GLM-5.2 took on…
Z. ai has open-sourced its RL infrastructure, the slime framework, which enabled efficient OPD post-training of GLM-5.2 in about two days. slime is an LLM post-training framework for RL scaling that integrates Megatron and SGLang, and has been battle-tested by frontier models like GLM, Qwen, DeepSeek, and Llama.
@jerryjliu0: The latest RAG trend for the current agent harnesses (Codex, Cowork) is to do two passes of document processing to solv…
The article discusses a two-pass document processing trend for AI agents, where a fast OSS pass enables efficient retrieval and a VLM-based pass ensures accuracy, promoting Llama Index's LiteParse and LlamaParse tools to enhance cost and performance.
@yifanzhang_: https://thinkingmachines.ai/news/introducing-inkling/… RoPE is dead, Long live GRAPE!
Thinking Machines AI releases Inkling, an open-weights Mixture-of-Experts model with 975B total parameters (41B active), supporting text, images, and audio over a 1M token context window. It is a broad foundation model designed for fine-tuning via their Tinker platform, with a smaller Inkling-Small variant also previewed.