Alternatives
Products that do what I implemented the Kimi K3 paper from scratch in PyTorch does
- 1
- 2
- 3
- 4
- 5
- 6
- 7IS
I wanted to take kimi k3 for a spin. It turned my simple one sentence prompt to this. Repo here. https://github.com/praveer13/ilya-papers-quest Well, I'm mindblown. Very humbling for me as a software engineer. Took couple hours for it to build this completely autonomously. And it was all from its mobile app. It couldn't render this though from within the app - it does have a feature to preview any website and publish it on kimi's domain - but it didn't work for this. I had to put it on github pages. It doesn't store anything btw - all progress is tracked in your browser…
Jul 2026 · ilya-papers-quest.naigap.com
- 8
- 9AN
Kimi K3 has 2.78 trillion parameters and ships as 1.42 TB of weights. It clearly does not fit in the memory of a laptop. But K3 is a Mixture-of-Experts model. For each token, only a small fraction of its 896 experts per layer is activated. That changes the problem: the entire model does not need to be resident in RAM, as long as the weights required by each token can be reached quickly enough. We built WASTE — the Weight-Aware Streaming Tensor Engine — to explore that idea. WASTE keeps the dense, repeatedly used part of the model resident in memory, stores the routed experts in an…
Jul 2026
- 10KA
2010 · thingsaaronmade.com
- 11
- 12
- 13
- 14GA
I'm starting to implement a barebones version of pytorch in Go. The primary motivation is: 1. I want to better learn Pytorch and how it works so what better way than to just re-implement some of its core features. 2. I write mainly in Go and haven't come across a lot of ML support in Go 3. I'd rather have a Go ML service instead of spinning up additional infrastructure to just support a python ML service in my Go projects 4. Go's static typing, native concurrency (avoid GIL problem in python), efficient memory management, single binary deployment and more make it a better interface compared…
2024
- 15
- 16
Testing Kimi K3’s Ability Through Practical Use Cases
Jul 2026 · youtube.com
- 17GB
Hey HN, We’re excited to share PySpur, an open-source tool that provides a graph-based interface for building, debugging, and evaluating LLM workflows. Why we built this: Before this, we built several LLM-powered applications that collectively served thousands of users. The biggest challenge we faced was ensuring reliability: making sure the workflows were robust enough to handle edge cases and deliver consistent results. In practice, achieving this reliability meant repeatedly: 1. Breaking down complex goals into simpler steps: Composing prompts, tool calls, parsing steps, and branching…
2024 · github.com
- 18NT
I built a CLI tool that turns codebases and PRs into diagrams so you can quickly understand how things fit together. Originally made it because I couldn't follow my own AI-generated repos. Just shipped a big update: - Switched from D2 to Mermaid for rendering - Tree-sitter AST parsing + agentic flow instead of raw LLM calls. ~50x faster. - Works on any GitHub repo or PR, not just local - Dropped the web frontend, it's just a CLI now - Published as a pip package Still a ton to improve and I'm building fast. Feedback, issues, PRs all welcome.
Feb 2026 · github.com
- 19K0
2021 · github.com
- 20KK
hey HN, this is sina. i've had some cloudflare credits expiring on may 14 and was wondering what to do with them. when kimi k2.6 dropped and it was available on workers ai, i figured i'd build an open-source claude code clone with it. didn't think too much about it. (people asked if i know about opencode and tbh i learned about them only after i built this. but they seem really brilliant.) anyway, kimiflare is a CLI coding agent, basically claude code but powered by kimi k2.6 on cloudflare workers ai. it's at v0.57.0 and has gotten 12k+ npm downloads, 137 github stars, and PRs from 4…
May 2026
- 21FM
As the title and description of the GitHub repo suggest, I’m working on a small project for purely educational purposes, with the goal of implementing generative model inference (small models capable of modeling 2D distributions) based on the Flow Matching paradigm in C. I’ve worked on generative AI models based on Flow Matching from a more “abstract” perspective, using frameworks like PyTorch, and I wanted to understand what goes on behind the scenes. The repository is still a work in progress and is also one of my first "serious" projects in C.
Jul 2026 · github.com
- 22
Learn PyTorch from scratch with simple examples.
Aug 2026 · khayyamshah2007.blogspot.com
- 23
- 24
NotebookLM, Gamma, Manus, and Kimi turn research into decks.
Apr 2026
Ranked by how close each launch is in meaning, then by votes. Refine with a description →