Qwen3 Python Packages

vllm

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

ms-swift

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5.3, Gemma4, Llava, Phi4, ...) (AAAI 2025).

hud-python

RL environments + evals for AI agents. Define once, train anything.

hud

RL environments + evals for AI agents. Define once, train anything.

vllm-cpu-nightly

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

vllm-tpu

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

sigit-code

A modular local inference LLM coding agent. Core component of siGit Factory.

nemo-automodel

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

duplexjev

DuplexJev-32B and DuplexJev-4B: speech decision models for full-duplex voice agents. Typed single-token readout from a frozen speech LLM, served with vLLM. Try it: api.adventists.cn/duplexjev

qwen3-embed

Lightweight Qwen3 text embedding and reranking via ONNX Runtime and GGUF

jev-style

Small, calibrated decision models on your own machine: systemone-compatible local server, 6 agent skills, Claude Code guard, MCP tools. Weights on Hugging Face.

tinyjev

A tiny jev-like model that answers Choice, Score and Noul questions in one forward pass and returns calibrated probabilities. MLX or PyTorch, fully offline, System One compatible.

geniex

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

duplexjev-vllm

DuplexJev-32B and DuplexJev-4B: speech decision models for full-duplex voice agents. Typed single-token readout from a frozen speech LLM, served with vLLM. Try it: api.adventists.cn/duplexjev

geniex-llama-cpp

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

geniex-qairt

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

steadytext

Deterministic text generation and embeddings with zero configuration

qwen-reverse

Reverse-engineered async Python client for chat.qwen.ai — text chat, streaming with real-time reasoning, tool calling, image and video generation. No official API key required (works anonymously).

vllm-xft

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

ai-dynamo-vllm

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

deepsearcher

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

echoalign-asr-mlx

Local Apple Silicon CLI for ASR, subtitles, WebVTT/SRT, and timestamp-aligned JSON with MLX + Qwen3

vllm-dgxspark-psychoscales

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

pipecat-duplexjev

DuplexJev-32B and DuplexJev-4B: speech decision models for full-duplex voice agents. Typed single-token readout from a frozen speech LLM, served with vLLM. Try it: api.adventists.cn/duplexjev