Moe Python Packages

nvidia-cudnn-frontend

cuDNN Frontend is NVIDIA's modern, open-source entry point to the cuDNN library and a growing collection of high-performance open-source kernels.

flashinfer-python

FlashInfer: Kernel Library for LLM Serving

sglang

SGLang is a high-performance serving framework for large language models and multimodal models.

vllm

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

flashinfer-cubin

FlashInfer: Kernel Library for LLM Serving

sglang-kernel

SGLang is a high-performance serving framework for large language models and multimodal models.

sgl-kernel

SGLang is a high-performance serving framework for large language models and multimodal models.

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).

vllm-cpu-nightly

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

tensorrt-llm

TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.

llamafactory

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

experts4bit-qlora

Fine-tune and serve large Mixture-of-Experts models on one GPU, with 4-bit experts in GPU memory, RAM or SSD.

vllm-tpu

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

grouped-nf4-gemm

4-bit GPU kernels that compute directly on packed Mixture-of-Experts weights, for training and inference.

freetoken

FreeToken brings datacenter-scale model serving to your desktop. Run massive models locally, fast and efficiently.

awex

A high-performance RL training-inference weight synchronization framework, designed to enable second-level parameter updates from training to inference in RL workflows

loggetta

Plan and run Mixture-of-Experts fine-tuning on one GPU: check the machine, fit the model, and keep a report of each run.

pion-vllm-mlx

Pion — the memory engine for AI inference

moe-l2

MoE expert offload for low-VRAM GPUs — run 100B+ MoE models (DeepSeek, Qwen, Mixtral) on 8 GB cards. Expert cache with LRU hot experts, OpenAI-compatible proxy, GGUF multi-shard.

quantprobe

Run a 110B on a 2016 PC with 16 GB RAM. Know your tok/s before you download. Placement beats budget: predicts speed + memory fit for any GGUF on your exact hardware, self-calibrates, emits the exact llama.cpp command — or 'quantprobe auto' does it all. Falsification-tested laws; misses published at full size. pip install quantprobe

sglang-kt

SGLang is a high-performance serving framework for large language models and multimodal models.

mlx-flash

Run AI models too large for your Mac's memory — at near-full speed. Intelligent expert caching, speculative execution, and 15+ research techniques for MoE inference on Apple Silicon.

abliterix

Automated alignment adjustment for LLMs — direct steering, LoRA, and MoE expert-granular abliteration, optimized via multi-objective Optuna TPE.

lsglang

SGLang is a high-performance serving framework for large language models and multimodal models.