- Seoul, South Korea
-
23:36
(UTC +09:00) - https://junbuml.ee
- @__Beomi__
- https://scholar.google.com/citations?user=wzH5UWUAAAAJ&hl=en
- https://huggingface.co/beomi
Stars
This is a public repository to enable researchers to begin their journey of self-hosting data from Semantic Scholar.
ToolOrchestra is an end-to-end RL training framework for orchestrating tools and agentic workflows.
Latent Collaboration in Multi-Agent Systems
An unofficial PyTorch port (and subsequent modification) of `NJU-Jet/SR_Mobile_Quantization`.
[TMLR 2025] Thera: Aliasing-Free Arbitrary-Scale Super-Resolution with Neural Heat Fields
Distributed Compiler based on Triton for Parallel Systems
A Python-embedded DSL that makes it easy to write fast, scalable ML kernels with minimal boilerplate.
Framework to reduce autotune overhead to zero for well known deployments.
A lightweight, local-first, and 🆓 experiment tracking library from Hugging Face 🤗
Example of using the tensor op for matmul in Metal 4.
Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support
Backend.AI is a streamlined, container-based computing cluster platform that hosts popular computing/ML frameworks and diverse programming languages, with pluggable heterogeneous accelerator suppor…
The power of Claude Code / GeminiCLI / CodexCLI + [Gemini / OpenAI / OpenRouter / Azure / Grok / Ollama / Custom Model / All Of The Above] working as one.
A python module to repair invalid JSON from LLMs
Allow torch tensor memory to be released and resumed later
MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers
🇺🇦 Your meetings at your fingertips in the macOS menu bar
Fault tolerance for PyTorch (HSDP, LocalSGD, DiLoCo, Streaming DiLoCo)
A high-performance parallel SSH command execution tool for cluster management