Mxfp4 Python Packages

auto-round

A simple and effective post training quantization toolkit for high-accuracy low-bit LLM inference|简洁且高效的后训练量化工具包

auto-round-nightly

A simple and effective post training quantization toolkit for high-accuracy low-bit LLM inference|简洁且高效的后训练量化工具包

auto-round-lib

A simple and effective post training quantization toolkit for high-accuracy low-bit LLM inference|简洁且高效的后训练量化工具包

experts4bit-qlora

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

grouped-nf4-gemm

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

auto-round-hpu

A simple and effective post training quantization toolkit for high-accuracy low-bit LLM inference|简洁且高效的后训练量化工具包

block-streamer

Stream PyTorch model blocks from NVMe or pinned CPU memory with a bounded GPU residency budget. LoRA-finetune models far larger than host RAM on one GPU - Qwen3-VL-32B and gpt-oss-120b train in under 6 GB of VRAM.

auto-round-kernel

A simple and effective post training quantization toolkit for high-accuracy low-bit LLM inference|简洁且高效的后训练量化工具包

e4b

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

experts4bit

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

grit-datatype

GRIT — Grouped Reduced-precision Interchange Type: a checkable 64-byte descriptor + contract for block-scaled, sparse, sub-byte tensors. Spec, conformance vectors, and 5 zero-dependency implementations (C, C++, Rust, Python, TypeScript). grit scan audits GGUF/safetensors files you already have.

e4b-qlora

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

experts-mxfp4

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

grouped-mxfp4-gemm

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

expertsnbit

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

gnf4

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

nf4gemm

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

auto-around

PTQ-Level Efficiency, QAT-Level Accuracy|训练后量化的效率，量化感知训练的精度