AI Developer Cloud. AI infrastructure developers trust. https://teapaw.org/t.co/PWVZocfp6D
Joined March 2022
- Tweets874
- Following18
- Followers9.6K
- Likes856
Pinned Tweet
Someone died at a haunted masquerade ball. Five suspects will answer anything you ask, and at least one of them is lying.
Build "Murder at Hollow Manor" with Qwen3 32B and FLUX.1 Schnell on Runpod Public Endpoints 🎃runpod.io/blog/halloween-mys…
No weekend plans yet? Well, we have a suggestion.
Kimi K3.1 Pro is live on Runpod. Point your client at it and experiment.
See how you can get started here: runpod.io/blog/kimi-k3-1?utm…
@Kimi_Moonshot
On Nov 12, we'll go live together with @Kimi_Moonshot on how to run long-horizon agents with Kimi K3 and K2.
Best practices, token management, and a demo.
Register here: resources.runpod.io/kimi-in-…
868,000+ LoRAs in a single month. 500+ GPUs running at once.
Not one big training run, but hundreds of thousands of creators fine-tuning concurrently.
✨@Kimi_Moonshot K3.1 Pro from Moonshot is now on Runpod Public Endpoints!
This is a 3T-class open-weight model with a 1M token context window, at $2 per 1M input and $10 per 1M output tokens.
Both are OpenAI SDK compatible. Point the base URL at Runpod, keep your client, and switch models with one string in the request.
Full walkthrough with Playground, curl and Python: runpod.io/blog/kimi-k3-1?utm…
“Mixed precision halves your training memory.”
We did the math and found that it doesn’t.
Here's what we found: runpod.io/articles/guides/fp…
Serverless workers cost about 2.3x more per taken than a Pod.
Anything below that, Serverless wins. More than that? Go with Pods.
We benchmarked both in the article here:
runpod.io/blog/serverless-gp…
Batch Inference is now generally available on Runpod Serverless.
Batch runs on dedicated workers that are separate from your /run traffic, so a large job doesn’t take workers away from interactive requests.
runpod.io/blog/batch-inferen…
A big embedding backfill hits your max workers limit though nobody is waiting on it.
Batch Inference on Serverless takes up to 3 million requests a day on dedicated workers, on your own model.
Limits depend on your account.
runpod.io/blog/batch-inferen…
Join Runpod and @bem_hq for drinks, games and good conversation during MLOps World!
Meet the teams building AI infrastructure, catch a few quick lightning talks, and stay for the raffle.
Monday, November 16, 6 to 8pm at Tapville Social, Austin.
Space is limited, so register early: lu.ma/runpod-bem-austin
Wondering what changed in AI compute this year?
We have the data, and we'll share it with you on Thursday.
Register through the link below; we have a session at 6 am PT & 11 am PT!
resources.runpod.io/where-ai…
We’ll be at Open Data Science Conference (ODSC) West in Burlingame this week.
250+ speakers and 9 tracks covering everything from AI infrastructure to agentic systems.
Come and find us there.
PS: Don't miss Greg Wester's talk on Tuesday at 2:35 PM.
Gemma’s share of Runpod text endpoints:
March: 5.5%
April: 18.2%
July: 12.4%
The release spike was real. So was the pullback. July adoption still stood at more than twice its March level.
runpod.io/reports/fall-2026-…
Community feedback told us to update our PyTorch templates.
The new lineup covers PyTorch 2.6, 2.7, 2.8, 2.9, 2.12, and 2.13. Each version is available with several CUDA versions.
Find the full breakdown here: runpod.io/blog/rebuilding-py…
