Impactful scheduling for GPU clusters
Ai2 says it replaced a priority-based GPU scheduler with a system combining GPU-time budgets, hierarchical fair-share allocation and a workload minimum-runtime contract.
source-linked1
Raw Signals
Dated, source-linked observations imported from the QWG AI archive.
These are evidence records, not finished editorial conclusions.
Key takeaway
Across 1332 observations, most signals relate to model behavior, evaluation discipline, and real-world agent operations. Strong evidence clusters around tooling, memory, routing, and productized agent execution.
agentscoding agentsagent harnessagent runtimemodelsagent protocols
What this means
Teams are moving from experiments to systems. The emphasis is on verifiable behavior, operational safety, and measurable outcomes—especially in agent memory, evaluation rigor, and forward-deployed engineering.
Filters (current page)
1-10 of 10 matching raw signals on this page
lusters-91fb66 notableresearch
source-linked1ia-vera-d8d51c notablereleasevLLM adds day-0 support for NVIDIA Vera Rubin NVL72 via nightly cu134 containers.
vLLM says its runtime now supports NVIDIA Vera Rubin NVL72, with daily container builds and support for models including DeepSeek, Moonshot AI, Z.ai, and MiniMax.
source-linked1-claude-72da39 notableupdateThe Gauntlet Loop: The Prompting Method Behind Claude of Duty
Matt Shumer’s article describes the Gauntlet Loop, a method for repeated agent improvement: give a lead agent a goal and a concrete quality reference, split the work into parts, and have separate critics compare results against that reference.
source-linked1foundry-9468ed notablereleaseMicrosoft launches Decision-1 model in Foundry
Microsoft has made Microsoft-Decision-1 available in Microsoft Foundry, according to the supplied report.
source-linked1-rerank-976fba notableannouncementShared vs. Dedicated AI Inference: Embed & Rerank
# Cohere: sizing shared and dedicated inference for Embed and Rerank
source-linked1able-on-a235bd notableannouncementDecision-1 from @MicrosoftAI is now available on AI Gateway.
Vercel says Microsoft Decision-1 is now available through AI Gateway.
source-linked1-plus-a-257891 notablereleaseIntroducing Clef-omni with full multimodality, plus a faster Clef and a cheaper Clef-flash
Cloudflare announced an expansion of its Clef decision-model family with Clef-omni, which it says processes audio, video, images, and text in a single pipeline.
source-linked1-vercel-a97d54 notablereleaseYour agents can now buy domains with Vercel CLI.
## Vercel CLI lets agents prepare domain purchases, with human approval at checkout
source-linked1cisions-78299e notablereleaseLangSmith LLM Gateway now supports the OpenAI Decisions API.
LangSmith’s documentation now describes support for the OpenAI Decisions API through the LLM Gateway.
source-linked1t-using-810711 notableannouncementA new feature for my blog, built using my voice
Simon Willison shipped a newsletters archive for his blog after building most of it through Codex voice mode in the ChatGPT desktop app, connected to a local development environment.
source-linked1
No raw signals match these filters.
Source & exports
Primary indexes and programmatic access to this dataset.
Archive contractEnglish normalized copy, Telegram provenance, public sources only