Viewing profile — k2so

Location: Göttingen, Germany Remote: Yes Willing to relocate: Yes, within in Germany Technologies: Python, FastAI, vLLM, PTQ, Inference, Model Training, Transformers, Elastic Searc…

Location: Göttingen, Germany Remote: Yes (preferred; hybrid also fine) Willing to relocate: No (remote, or hybrid within Germany) Technologies: Python, Go, search & retrieval, rank…

Location: Göttingen, Germany (work authorization available) Remote: Yes (preferred) Willing to relocate: Yes (anywhere in Germany, open to EU) Technologies: Python, Go, PyTorch, vL…

Yeah, for a single GPU inference, considering the higher VRAM and FP4 support on the RTX 6000, it should fit larger models as well than the H100.

Author here. I wanted to train Nanochat d26 to GPT-2 level and had to pick between three H100 variants on Runpod. SXM was the most expensive per hour but cheapest to finish: SXM: 7…

Scroll to visualise steps is such a great idea! Great writeup.

Interesting work, in the examples I can see that quite a few of them have the teracotta/warm-cream colour palette, was that an explicit choice to keep them in the prompts? From the…

KARMA-OpenMedEvalKit is an expandable toolkit for assessing AI models in medical applications, featuring multiple healthcare-focused datasets with particular emphasis on the Indian…

I make an argument for Model context protocol, and how it can shape the entire ecosystem

Beyond the developer, the user massively benefits from MCP. Like you said, using any other SDK to build is a very valid approach but then you are tied down to a single client that …

A neat trick in Vespa (vectors DB among other things) documentation is to use hex representation of vectors after converting them to binary. This trick can be used to reduce your p…

LLMs = Latency? That's how most of us perceive it. When examining the timing breakdown of a request on Claude, you'll notice that the majority of the time is spent in Content Downl…

In one of my earlier jobs a few years back, we were training deep learning models on VMs with GPUs, back then the tooling was not as extensive (vs-code did not have the remote ssh …

Easier to use libraries over highly complicated (supposedly performant) have a significant advantage in driving more adoption. Recently I was trying to generate text embeddings fro…

This is awesome, are you contributing this to candle or is it a standalone package?

I very strongly relate to this, it's been close to 3 months, since I have started working on a blog built on Quarto, and all I have so far is a elaborate design and a half complete…

This was my first thought too, after reading through their blog. This feels like a no-frills website made by an engineer, who makes things that just work. The documentation is grea…

Distill for R Markdown is a great alternative too. I really like the layout and the flexibility you get with the plots. The site can be hosted directly on github pages and you can …

Tomorrow and Tomorrow and Tomorrow - This was best read of 2023 for me. The narration is very immersive and the author makes you very invested in the story. Shows the messy, compli…