vLLM Semantic Router Releases d3-ultra: A 27B Open Multimodal Decision Model
vLLM Semantic Router released d3-ultra, a 26.09B Apache-2.0 multimodal decision model scoring 87.2 on its own SR-Text benchmark.
Topic
#model-evaluation
11 篇笔记
How To Use Decision Models for Evals
Co-authored with Antaripa Saha.Decision models have exploded onto the scene recently, starting with TypeSafe’s Jev, followed by Perplexity’s...
Evaluating OpenWiki with WikiBench
OpenWiki is our open source agent for generating and maintaining codebase documentation. As we improve OpenWiki, we’ve needed to measure two...
SemiAnalysis 发布 AgentX InferenceXv3 研报，Mooncake 成为关键基础设施
SemiAnalysis 发布 AgentX InferenceXv3，用大规模真实 Agentic workload 重新审视推理系统性能。随着长上下文、多轮交互和 KV Cache 复用成为常态，Agentic Inference 正从“拼算力”走向系统级优化，而 Mooncake 也正在其中扮演越来越重要的基础设施角色。
The AI Engineering Skills Map
I am delighted to present The AI Engineering Skills Map. AI allows us to build software very differently today than in 2022, and everyone wi...
Why Software Factories Fail
or: the harness is not enoughUpdate - the talk version of this post is live on youtube: https://www.youtube.com/watch?v=Ib5GBkD555M Part 1 i...
Controlling Reasoning Effort in LLMs
How LLMs Learn Low-, Medium-, and High-Effort Reasoning Modes
Qwen Studio
Qwen Studio offers comprehensive functionality spanning chatbot, image and video understanding, image generation, document processing, web search integration, tool utilization, and artifacts.
Loop Driven Development, in practice
In Loop Driven Development I made an argument: when coding agents do the implementation, the engineering that matters moves to the feedback ...
Dreaming: Better memory for a more helpful ChatGPT
ChatGPT introduces a new memory system to better remember preferences, keeping context fresh and relevant across conversations.
Editing Files at 1000 Tokens per Second
A new model and inference method for high-accuracy full-file edits at 1000 tokens/s.