5 8 3

Erik Kaunismäki

erikkaum

https://www.erikkaum.com/

AI & ML interests

None yet

Recent Activity

upvoted an article 1 day ago

Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM

liked a Space 22 days ago

nanotron/ultrascale-playbook

upvoted an article 28 days ago

From Chunks to Blocks: Accelerating Uploads and Downloads on the Hub

View all activity

Organizations

erikkaum's activity

upvoted an article 1 day ago

Article

Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM

2 days ago

• 197

liked a Space 22 days ago

2.24k

The Ultra-Scale Playbook

🌌

The ultimate guide to training LLM on large GPU Clusters

upvoted an article 28 days ago

Article

From Chunks to Blocks: Accelerating Uploads and Downloads on the Hub

30 days ago

• 49

upvoted 2 articles about 2 months ago

Article

Introducing multi-backends (TRT-LLM, vLLM) support for Text Generation Inference

Jan 16

• 71

Article

Train 400x faster Static Embedding Models with Sentence Transformers

Jan 15

• 159

upvoted a collection 2 months ago

Cosmos

Collection

The collection of Cosmos models • 31 items • Updated Jan 17 • 269

liked a Space 4 months ago

Bluesky DID Lookup

🦋

Find DID for Bluesky handle

posted an update 4 months ago

Post

1749

A while ago I started experimenting with compiling the Python interpreter to WASM.

To build a secure, fast, and lightweight sandbox for code execution — ideal for running LLM-generated Python code.

- Send code simply as a POST request
- 1-2ms startup times

Hack away:
https://github.com/ErikKaum/runner