qwen3

A high-throughput and memory-efficient inference and serving engine for LLMs

🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, Phi4, ...) (AAAI 2025).

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!

Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code

Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.

📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉

A native macOS app that allows users to chat with a local LLM that can respond with information from files, folders and websites on your Mac without installing any other software. Powered by llama.cpp.

A powerful Zotero AI and MCP plugin with ChatGPT, Gemini 3.6, Claude Fable 5, Claude Sonnet 5, DeepSeek V4, Grok, OpenRouter, Kimi k3, GLM 5.2, SiliconFlow, GPT-oss, Gemma 4, Qwen 3.7

ASR/STT subtitle generator. Uses Qwen3-ASR, local LLM, Whisper, TEN-VAD. Noise-robust for JAV

kubewall - Single-Binary Kubernetes Dashboard with Multi-Cluster Management & AI Integration. (OpenAI / Claude 4 / Gemini / DeepSeek / OpenRouter / Ollama / Qwen / LMStudio)

Talk to your Mac, query your docs, no cloud required. On-device voice AI + RAG

🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support

🚀🚀🚀A collection of some awesome public projects about Large Language Model(LLM), Vision Language Model(VLM), Vision Language Action(VLA), AI Generated Content(AIGC), the related Datasets and Applications.

MimikaStudio - A local-first application for macOS (Apple Silicon) + Agentic MCP Support

Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2

a magical LLM desktop client that makes it easy for *anyone* to use LLMs and MCP

Zig INferenCe Engine — Local LLM inference on AMD GPUs and Apple Silicon

Fully uncensored, capability-enhanced abliteration of Qwen3.6-27B. NVFP4 + z-lab DFlash speculative decoding (n=12) on the unified ghcr.io/aeon-7/aeon-vllm-ultimate:latest container, tuned for long-context draft acceptance on DGX Spark. 6 HF variants (BF16/NVFP4/MTP/MTP-XS), docker-compose, and QuickStart.

Qwen3.8-27B on a single RTX 3090 with vLLM: ~1,000 tok/s at 64 concurrent (int8 tensor-core GEMMs, fp16 DeltaNet state), ~114 tok/s single-user at default sampling / ~124 greedy (MTP drafts, own-output draft vocab, calibrated int4 lm_head, split-KV verify attention), 150k-262k context; patches, requant scripts, benchmarks