Skip to content
View khotyn's full-sized avatar
😌
Focusing
😌
Focusing

Organizations

@acug @sofastack

Block or report khotyn

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse

Starred repositories

Showing results

Secure, fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in multi-language ruleset (N…

Go 53,439 4,391 Updated Nov 17, 2026

DeepSeek Harness: Everything is a Plugin.

TypeScript 282,805 35,041 Updated Nov 13, 2026

Context7 Platform -- Up-to-date docs for AI agents

TypeScript 64,986 3,266 Updated Nov 17, 2026

Supercharge your AI agents with data from the web and beyond. Building the library for superintelligence. 🔥

TypeScript 202,519 10,604 Updated Nov 17, 2026

Markdown Architectural Decision Records

Markdown 2,646 470 Updated Nov 13, 2026

The AI that really does things. Any OS. Any Platform. The lobster way. 🦞

TypeScript 394,630 82,904 Updated Nov 17, 2026

A simple, performant, and scalable Jax LLM!

Python 2,465 648 Updated Nov 17, 2026

an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM

Rust 56,711 6,607 Updated Nov 17, 2026

Incredibly fast JavaScript runtime, bundler, test runner, and package manager – all in one

Rust 96,727 5,289 Updated Nov 17, 2026

A high-performance inference engine for LLM, VLM and DiT models, optimized for diverse AI accelerators. It is hosted in OpenAtom Foundation.

C++ 1,623 342 Updated Nov 17, 2026

Open Lakehouse Format for Multimodal AI. Convert from Parquet in 2 lines of code for 100x faster random access, vector index, and data versioning. Compatible with Pandas, DuckDB, Polars, Pyarrow, a…

Rust 7,348 949 Updated Nov 17, 2026

Public repository for Agent Skills

Python 196,482 23,047 Updated Nov 16, 2026

The best ChatGPT that $100 can buy.

Python 60,627 8,512 Updated Sep 7, 2026

An open, programmable decision layer for models and compute.

Go 6,492 1,126 Updated Nov 17, 2026

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…

TypeScript 155,996 25,023 Updated Nov 17, 2026

Train speculative decoding models effortlessly and port them smoothly to SGLang serving.

Python 1,289 395 Updated Nov 17, 2026

Data driven agentic landscapes and insights. Produced by Ant Open Source and inclusionAI.

HTML 560 40 Updated Sep 27, 2026

An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)

Python 10,162 1,065 Updated Nov 3, 2026

[MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

Python 3,667 328 Updated Jul 17, 2025

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

Python 36,641 4,007 Updated Nov 17, 2026

verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

Python 24,264 4,921 Updated Nov 17, 2026

iTerm2 is a terminal emulator for Mac OS X that does amazing things.

Swift 18,293 1,558 Updated Nov 17, 2026

[HPCA 2026] AI Accelerator Benchmark focuses on evaluating AI Accelerators from a practical production perspective, including the ease of use and versatility of software and hardware.

Python 405 130 Updated Apr 22, 2026

The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.

Python 5,914 662 Updated Nov 17, 2026

DeepGEMM: clean and efficient BLAS kernel library on GPU

Cuda 9,201 1,534 Updated Oct 20, 2026

CUDA Templates and Python DSLs for High-Performance Linear Algebra

C++ 10,737 2,184 Updated Nov 6, 2026

FlashMLA: Efficient Multi-head Latent Attention Kernels

C++ 13,275 1,278 Updated Oct 27, 2026

A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations

Python 19,680 1,603 Updated Nov 13, 2026

SGLang is a high-performance serving framework for large language models and multimodal models.

Python 38,977 10,568 Updated Nov 17, 2026

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Python 76,083 9,381 Updated Nov 17, 2026
Next