Skip to content
View kiminh's full-sized avatar

Block or report kiminh

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

354 results for sponsorable starred repositories
Clear filter

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

C 24,371 2,374 Updated Nov 8, 2026

AOTInductor Weight Streaming from PyTorch Models

C++ 1 Updated Aug 27, 2026

Full-parameter reward-model training sharded with FSDP2, verified on CPU (collective counts, bitwise resume from a sharded checkpoint), with a GPU sweep on 4x L40S planned for throughput, memory, s…

Python 1 Updated Nov 3, 2026

Personal daily InShorts-style digest for LLM/SLM inference-engineering news

Python 1 1 Updated Nov 15, 2026

Nauti-Strata: Speculative lookahead MoE scheduling, dynamic PCIe prefetching, and legacy compute (sm_60/AVX) acceleration

C++ 1 Updated Nov 8, 2026

Jev-like family of decision models built on top of Qwen3.5/3.8 you can train and run on your own

Python 9,996 684 Updated Nov 15, 2026

Open-source Answer Engine Optimization (AEO) and Generative Engine Optimization (GEO) platform. Track how ChatGPT, Claude, Perplexity, Gemini, Copilot, Grok, and Google AI Overviews mention and cit…

TypeScript 602 168 Updated Nov 14, 2026

High-performance, SIMD-accelerated vector search engine and MCP server for .NET 10. Optimized for LLM embeddings and semantic search.

C# 6 Updated Nov 14, 2026

Fork of LM Evaluation Harness Suite for evaluating benchmarks in paper titled "PLDR-LLMs Learn A Generalizable Tensor Operator That Can Replace Its Own Deep Neural Net At Inference"

Python 6 Updated Oct 5, 2026

O(N·K) multi-head attention for PyTorch — a sparse drop-in replacement for dense scaled-dot-product attention.

Python 1 1 Updated Jul 3, 2026

The open-source CapCut alternative

TypeScript 98,524 9,850 Updated Sep 24, 2026

TensorDict is a pytorch dedicated tensor container.

Python 1 Updated Jun 9, 2024

Fast, fully fledged murmur3 in Go.

Go 359 17 Updated Nov 9, 2026

Open-source swarm intelligence engine — simulate hundreds of AI agents to predict outcomes. Includes MCP server for Claude.

Python 8 1 Updated May 21, 2026
Shell 26 3 Updated Sep 3, 2026

有时我们完全不需要预装载 Skill 进上下文

TypeScript 1 Updated May 31, 2026

# TurboQuant v3 (INT4 + AWQ + Protected Channels + Low-Rank) This notebook demonstrates a **TurboQuant-like** quantization algorithm: - Group-wise INT4 quantization - Activation-aware scaling (AWQ-…

Python 17 Updated Mar 29, 2026

Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1

Python 1 Updated May 22, 2026

An adaptive continually learning hybrid RAG Agent for content, curation, and persona growth. It combines spaCy-based NLP, a persona graph, BM25 retrieval, a truth gate, confidence scoring, and loca…

Python 13 2 Updated Nov 15, 2026

An experimental pi extension that runs and manages qwen with llama.cpp

TypeScript 145 13 Updated May 11, 2026

本地优先的跨平台 Claude Code / AI Agent 桌面工作台:多 Agent 协作、Git Worktree、代码 Diff、技能市场、多模型、Computer Use、桌面宠物;支持微信、飞书、钉钉及 H5 等远程访问。 | Local-first Claude Code / AI Agent desktop workspace: multi-agent teams, Git…

TypeScript 15,448 8,619 Updated Nov 15, 2026

TokenSpeed is a speed-of-light LLM inference engine.

Python 2,931 415 Updated Nov 16, 2026

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode,DeepSeek Harness and more. Only official website: ccswitch.io

Rust 154,622 10,132 Updated Nov 15, 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 79,573 7,419 Updated Nov 16, 2026
TypeScript 1 Updated Apr 20, 2026

Evolutionary Multi-Objective Optimization

C 1 Updated Feb 19, 2021

Implementation of Inverse Reinforcement Learning (IRL) algorithms in Python/Tensorflow. Deep MaxEnt, MaxEnt, LPIRL

Python 687 145 Updated May 10, 2024

Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels.

Python 1,625 165 Updated Nov 13, 2026

Maximum Entropy and Maximum Causal Entropy Inverse Reinforcement Learning Implementation in Python

Jupyter Notebook 334 66 Updated Apr 21, 2024

Harness Engineering 学习指南 — 从概念理解到独立实践的深度学习档案

JavaScript 6,287 545 Updated Oct 31, 2026
Next