Skip to main content

cosmos3-quantization

Quantize Cosmos3 generator checkpoints to static-scale FP8 with the cosmos_framework.quantization recipe (NVIDIA TensorRT Model Optimizer): the Edge, Nano and Super video models and the Super Text-to-Image / Image-to-Video base and 4-step distilled students, exported as drop-in Diffusers-layout checkpoints with calibrated scales and an hf_quant_config.json that load on vLLM-Omni. Use when the user asks "quantize Cosmos3 to FP8", "make / calibrate / export my own FP8 Cosmos3 checkpoint", "run quantize_fp8_checkpoint", "DEMO=1 vs DEMO=0 calibration", or "what does the FP8 export contain". Do not use it to run inference with a published FP8 checkpoint (nvidia/Cosmos3-Edge-FP8, -Nano-FP8, -Super-FP8) — that is the FP8 route of cosmos3-inference-generate-media and of the Reasoner / Action / Transfer cookbook notebooks (their skills follow in later rows) — nor for the framework's load-time --quantization-method flags.

Datos de origen

Repositorio
NVIDIA/cosmos-framework
Última actividad en el origen
11 de noviembre de 2026 a las 05:17
Idioma detectado de SKILL.md
inglés
Estrellas
648
Forks
214

Opciones de instalación

De forma predeterminada está seleccionado el prompt que primero revisa el origen. Puedes cambiar a un comando directo o descargar una copia local.

Revisa los archivos de origen

Lee SKILL.md y los archivos complementarios que muestra SkillsMP antes de decidir si quieres instalarlo.

Explorador de archivos
6 archivos

Mostrando SKILL.md

SKILL.md
Instrucciones de origen · Vista previa de solo lectura
namecosmos3-quantization
descriptionQuantize Cosmos3 generator checkpoints to static-scale FP8 with the cosmos_framework.quantization recipe (NVIDIA TensorRT Model Optimizer): the Edge, Nano and Super video models and the Super Text-to-Image / Image-to-Video base and 4-step distilled students, exported as drop-in Diffusers-layout checkpoints with calibrated scales and an hf_quant_config.json that load on vLLM-Omni. Use when the user asks "quantize Cosmos3 to FP8", "make / calibrate / export my own FP8 Cosmos3 checkpoint", "run quantize_fp8_checkpoint", "DEMO=1 vs DEMO=0 calibration", or "what does the FP8 export contain". Do not use it to run inference with a published FP8 checkpoint (nvidia/Cosmos3-Edge-FP8, -Nano-FP8, -Super-FP8) — that is the FP8 route of cosmos3-inference-generate-media and of the Reasoner / Action / Transfer cookbook notebooks (their skills follow in later rows) — nor for the framework's load-time --quantization-method flags.