Star 总榜

Convert pdf and image files into markdown

vLLM + Qwen3.6-27B (BF16) OpenAI-compatible inference server on AMD Strix Halo (Ryzen AI Max+ 395, gfx1151). Vision input, 256K context, /v1/responses with separated reasoning, via TheRock ROCm.

The official repo for the paper "Optimizing LLM Inference Throughput via Memory-aware and SLA-constrained Dynamic Batching"

KONASH: Train knowledge agents that search, retrieve, and reason. Based on KARL (Databricks, 2026).

A Lightweight, Configuration-Driven, Flexible Fine-Tuning Framework for 🤗 Diffusers

[WSDM 2026] LookAhead Tuning: Safer Language Models via Partial Answer Previews

Implementation of ResFit, Residual Off-Policy RL for Finetuning Behavior Cloning Policies

Fine-tuning Resnet-50 FPN based DNN for road crack detection on RDD2022

Making MoE fine-tuning accessible to anyone with consumer hardware.

weighted category-balanced dataset builder for LLM fine-tuning

fine-tuning of the Segment-Anything model by MetaAI

Finetuned Deepseek 8b model for finance reasoning

Enterprise-grade LLMOps platform to accelerate the development and deployment of generative AI applications.

Code and supplementary materials for the research paper titled 'Advancing Geological Image Segmentation: Deep Learning Approaches for Rock Type Identification and Classification', published in Applied Computing and Geosciences (Elsevier).

CPU-first, eager-execution tensor/autograd runtime and LLM inference engine written in pure Zig

Build sovereign RAG systems with MAS‑RAG, Dual‑RAG, GraphRAG, Spatial‑RAG, multimodal pipelines, and vector search directly inside Oracle AI Database 26ai and Exadata.

Curated, research-grade catalog of public AI models with substantial support for the Kazakh language.

IntelliJ IDEA extension for Liberty

A theme 🎨 for IntelliJ IDEs based on the KDE Breeze Theme. Includes light ☀️ and dark 🌒 variants.

A SFTP Plugin for IntelliJ Ultimate Edition IDE, like IDEA, WebStorm, PHPStorm and more.