Skip to content
View tebjan's full-sized avatar
🌻
Focusing
🌻
Focusing

Organizations

@vvvv @stride3d @vl-pynet-ai

Block or report tebjan

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

Lapilli: Basalt ported to NVIDIA V100 (Volta, sm_70). Runs Qwen3.8-Flash-Next on V100 GPUs, with a chat web UI.

C++ 11 Updated Nov 20, 2026

Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)

Python 13,084 1,427 Updated Oct 17, 2026

Evaluating LLMs with fewer examples

Jupyter Notebook 188 22 Updated Jul 4, 2026

A local coding agent that talks to a model server you host. One Go binary with the web UI compiled in. The transcript, the tools and the state stay on your machine.

Go 13 1 Updated Nov 20, 2026

Agentic GraphRAG is an open source framework that builds a graph connecting your enterprise knowledge to the conversations your agents have and the decisions they make. Each decision links back to …

Python 65 5 Updated Nov 20, 2026
Jupyter Notebook 199 25 Updated Aug 27, 2025

Heavily compressed docker images for SWE Bench Verified

Go 9 1 Updated Oct 1, 2025

Bend 2: a fast language that blocks AI mistakes via proof. Install: curl -fsSL https://bend-lang.com/install.sh | sh

TypeScript 25,703 820 Updated Nov 18, 2026

Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent…

Python 2,774 348 Updated Nov 10, 2026

Open-source replacement for the MECHREVO, XMG and Eluktronics Control Center on Uniwill-based laptops. Controls CPU/GPU power, fans, battery, lighting and more directly through the EC. Native C++ f…

C++ 23 1 Updated Nov 20, 2026

A programming language for AI orchestrations

Rust 2,027 222 Updated Nov 18, 2026

Unofficial description of the CUDA assembly (SASS) instruction sets.

Python 286 26 Updated Nov 7, 2026

A GPU task manager for Windows, Linux, and WSL: per-process VRAM, GPU activity, and LLM model/KV-cache insights for NVIDIA, AMD, and Intel GPUs (plus Huawei Ascend on Linux).

Python 3,638 180 Updated Nov 19, 2026

Use GPT, DeepSeek, GLM, Gemini, Kimi and 400+ models in Claude Desktop's own model picker and in Claude Code, while staying signed in to your Claude subscription (1P, no gateway mode). Auto reasoni…

TypeScript 116 22 Updated Nov 20, 2026

A VL nuget to interact with Spotify's web API using JohnnyCrazy's SpotifyAPI-NET lib.

9 Updated Apr 25, 2023

Inference engine for Qwen3.x-27B (NVFP4) on one RTX 5090 (Blackwell, SM120), written from scratch in C++/CUDA

Python 17 5 Updated Nov 17, 2026

LLM Inference Engine for Metal, CUDA and Vulkan.

Zig 2,362 548 Updated Nov 21, 2026

Local inference engine optimized for NVIDIA Blackwell

C++ 1,597 242 Updated Nov 20, 2026

A live gauge for your local LLM inference engine in the menu bar: prefill and decode speed, prompt-cache hits, context, RAM and GPU. Works with Strata.

C# 9 1 Updated Nov 9, 2026

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

C 24,416 2,386 Updated Nov 8, 2026

Distributed AI/LLM for the people. Share compute privately or publicly to power your agents and chat.

Rust 4,186 528 Updated Nov 21, 2026

Open-source KVM software

C++ 2 Updated Nov 3, 2026

A local inference engine for Apple silicon, built around the model.

C++ 2,579 247 Updated Nov 17, 2026

Strata fork: Qwen3.8-Flash-Next 125B MoE in NVFP4 on one RTX 20-50 card (12 GB+) and 64 GB of RAM or more. Setup installs our GPTQ quants (huihui abliterated, OrcaRouter) from Hugging Face. CPU exp…

C++ 252 31 Updated Nov 20, 2026

Blazing fast Apple Silicon inference engine optimized for Qwen & Nemotron. OpenAI + Anthropic API compatible. Built by folks from nace.ai

C++ 835 116 Updated Nov 21, 2026

Agent skill that removes signs of AI-generated writing from text

Python 71,716 5,610 Updated Nov 19, 2026

Soft-MTP: Multi-Token Prediction Done Right. KL gradient recovery for faster speculative decoding and better language model training.

Python 108 13 Updated Nov 12, 2026

Tips & tricks to tune .NET workloads for better perf (mostly, targeting benchmarks).

C# 317 13 Updated Nov 10, 2026

Orca lets you run a fleet of bots with your own subscription (e.g. Claude Code, Grok, Agy, Codex). Available on desktop, mobile and remote runtime.

TypeScript 131,181 8,338 Updated Nov 21, 2026
Next