Skip to content
View Kiv's full-sized avatar

Block or report Kiv

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
Showing results

DeepSeek V4.1 Flash on 4x RTX PRO 6000 Blackwell: native weights, DSpark, vision, NVMe or locked RAM Engram offload.

Python 92 14 Updated Oct 17, 2026

DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm

C 24,385 2,378 Updated Nov 8, 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 10,164 1,065 Updated Nov 3, 2026

Aidan Bench attempts to measure <big_model_smell> in LLMs.

Python 323 16 Updated Jun 26, 2025

Data related to mind uploading project via prompt

HTML 31 6 Updated May 21, 2026

this is a TypeScript-based MCP server that implements a simple loom and makes it available for Claude to use.

JavaScript 24 3 Updated Feb 17, 2026

Machine Learning Engineering Open Book

Python 19,720 1,303 Updated Nov 12, 2026

Open-source desktop app for local LLMs. Text, vision, tool-calling, OpenAI/Anthropic-compatible API. 100% private.

Python 47,738 5,975 Updated Aug 17, 2026

David Attenborough narrates your life

Python 4,425 530 Updated Jul 23, 2026

Multiple NVIDIA GPUs or Apple Silicon for Large Language Model Inference?

Jupyter Notebook 1,939 75 Updated May 13, 2024

Code for the paper "Fishing for Magikarp"

Python 191 20 Updated Jul 10, 2026

AICI: Prompts as (Wasm) Programs

Rust 2,073 87 Updated Jan 22, 2025

PyTorch native post-training library

Python 5,817 764 Updated Nov 9, 2026

Blazingly 🔥 fast 🚀 memory vulnerabilities, written in 100% safe Rust. 🦀

Rust 5,450 114 Updated Sep 26, 2025

NVIDIA Linux open GPU with P2P support

C 1,445 146 Updated Nov 6, 2026

lightweight, standalone C++ inference engine for Google's Gemma models.

C++ 7,088 675 Updated Nov 17, 2026

Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.

Python 79,684 7,442 Updated Nov 17, 2026

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

Python 19,675 1,681 Updated Nov 8, 2026

Extremely simple implementation of path patching (aka causal scrubbing) in PyTorch.

Jupyter Notebook 5 Updated Oct 5, 2023

Stanford NLP Python library for understanding and improving PyTorch models via interventions

Python 920 121 Updated Mar 6, 2026

If tinygrad wasn't small enough for you...

Python 826 101 Updated Mar 9, 2024

Calculate token/s & GPU memory requirement for any LLM. Supports llama.cpp/ggml/bnb/QLoRA quantization

JavaScript 1,405 87 Updated Dec 3, 2024

Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.

HTML 249 90 Updated Aug 11, 2025
Python 8 3 Updated Nov 15, 2022

Named tensors with first-class dimensions for PyTorch

Jupyter Notebook 334 10 Updated Jun 14, 2023

Must-read Papers on Textual Adversarial Attack and Defense

Python 1,574 193 Updated Jun 4, 2025

The agent engineering platform.

Python 149,780 25,151 Updated Nov 17, 2026

A crude RLHF layer on top of nanoGPT with Gumbel-Softmax trick

Python 295 26 Updated Nov 25, 2023
Next