Swayam Singh

Strong version of you is dealing with all the inner demons silently, keeping all the chaos contained within you, hidden from the outside world. It'll get exhaustive sometimes and I am proud of you. Don't give up.

This trick is really interesting, Union's property of shared memory allows us to manipulate the same data by providing multiple views into the same memory address space, where each union member acts as a different decoder for the same bit pattern.

It's cool but also annoying that how "everyone" is product manager in open-source softwares.

A thread 🧵 TL;DR: We’re working on making NumPy’s cross-platform 128-bit float operations go brrr.... 🔥 So why are quad-precision (128-bit) linear algebra ops so slow and how we’re fixing it?

🚀 Meet FrugalRAG at #ICML2025 in Vancouver 🇨🇦! 📍 July 18 – VecDB Workshop, West 208–209 📍 July 19 – ES-FoMO Workshop, East Exhibition Hall A Come chat with me and @naga86 and learn how we're rethinking training efficiency and inference latency for RAG systems. 🧵

So I sat down, attached all the codebase I had, kept prompting and prompting and prompting (in between switched to the Linus's persona from his prime) 100x the productivity AND Closed the machine with "git restore ."

. @Ramneet_Singhh remember "we don't have users, but we have time" xD

🔥 New model alert! 🔥 Microsoft NextCoder-32B is now available in LocalAI! 🚀 This code-editing LLM boasts impressive performance & long context support. Get it running with: `local-ai run microsoft_nextcoder-32b` #LocalAI #LLM #Coding #NextCoder

📄 Paper 20/42: "NextCoder: Robust Adaptation of Code LMs to Diverse Code Edits" 🇮🇳 Tushar Aggarwal (Microsoft) LinkedIn: linkedin.com/in/tushar-agga… | Scholar: scholar.google.com/citations?user… 🇮🇳 Swayam Singh (Microsoft) LinkedIn: linkedin.com/in/swayam-sing… | Scholar:…

I planned a very cool thing for this PyCon India, but unfortunately some unplanned conflicts are happening. I'm sorry for if you were waiting for it, Next time then :)

This is really nice but no technical reports of either models and SWE-Bench as the only benchmark looks a bit suspicious. Don't get me wrong, Following the Mistral work a long way but it would be more acceptable if you guys open-up on some details and development of Devstral.

Healthy connections remain forever.

Team slack right now!! xD