Runpod

Runpod Flash is GA ⚡️ Flash is a Python SDK that lets you define infrastructure and deploy AI workloads directly from your terminal. Check it out: github.com/runpod/flash Blog: runpod.io/blog/flash-is-…

after extensive research, @runpod labs is happy to present: Poddy, your new pet in codex! npx petdex install poddy

@cosminnegruseri Keep an eye out, we're going to get some machines freed up.

haha, last few hours to submit in openai codegolf but no 8 gpu boxes available on @runpod

introducing wandler.ai - inference server based on @huggingface transformers.js - OpenAI-compatible - runs on mac, linux & win via cuda, coreml, dml, webgpu, wasm, cpu - tested llms from @liquidai, @Alibaba_Qwen & @GoogleDeepMind - embeddings & speech-to-text - works with @NousResearch Hermes - built in ts - open source as MIT - the first ever project from @runpod labs github.com/runpod-labs/wa…

It is crazy that now using the @googlegemma family of models, autoresearch, Codex or Claude Code, @elves_skill, @UnslothAI, and $20 to spend on @runpod, you can now get an industrial quality model that can be deployed on CPU done over a weekend with minimal observation even needed I actually trained two such models this weekend, one using Gemma 4 and the other using T5 Gemma 2 Not that long ago, these models would’ve been $10k-$50k and would’ve taken several people months The fact that the price and time have dropped so dramatically opens up all sorts of new use-cases that previously wouldn’t have made sense economically Wild times

Runpod just shipped Cost Centers. Now you get native spend tracking by team, project, or department, right in the console. Label any resource (Pods, Serverless, Network Volumes, Instant Clusters) and get per-label spend breakdowns on your monthly invoice. Unlabeled resources auto-group by creator. If you're running GPU workloads across multiple teams or projects and tired of spreadsheet reconciliation, this is a big one. Now in public beta for Runpod Teams.

@steipete glad we could make it in the selfie 😉

GUYS WE FOUND THE GUY WHO BUILT THE GITHUB MCP SERVER

We put a chat interface in the Runpod console. 23 tools across the full REST API. If you can do it in the dashboard, you can ask for it in chat. Find it in the console ;)

Runpod is now natively supported in @transformerlab! Add your API key and get experiment tracking, automatic checkpointing with failure recovery, persistent artifact storage, and interactive sessions (Jupyter, VSCode, vLLM) on your Runpod GPUs. Get started 👇

@aijoey glad we could help!

Thank you @runpod 10 minute run with the optimized config. val_bpb dropped from 1.51 to 1.39. 867 training steps on one 4080 gpu. compressed model: 15.8mb. just under the 16mb cap. 53 experiments found the config, one final run confirmed it. waiting on compute credits to see what 8 gpus do with this.

We're the compute partner for OpenAI's Parameter Golf challenge. Need credits? Apply at the link below!

Runpod is @OpenAI 's infrastructure partner for Parameter Golf, the first challenge in the Model Craft series. Train the best language model that fits in a 16MB artifact in under 10 minutes on 8×H100s. Together with OpenAI, we’re distributing up to $1M in credits across the challenge period to support experimentation and broaden participation. Enter the challenge and request credits 👇

The AI market looks nothing like the narrative. We have the production data to prove it. The State of AI: what 500K developers are actually running in 2026. Read the full report now 👇

Heading to @QCon London next week! If you’re working on: • GPU infrastructure • inference at scale • agent systems • production AI workloads Let’s talk about what you’re building. Come meet us on-site 👇