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.

Informations de source

Dépôt
NVIDIA/cosmos-framework
Dernière activité de la source
11 novembre 2026 à 05:17
Langue détectée de SKILL.md
anglais
Étoiles
648
Forks
214

Options d'installation

Le prompt qui vérifie d'abord la source est sélectionné par défaut. Vous pouvez passer à une commande directe ou télécharger une copie locale.

Vérifiez les fichiers source

Lisez SKILL.md et les fichiers associés affichés par SkillsMP avant de décider de l'installer.

Explorateur de fichiers
6 fichiers

Affichage de SKILL.md

SKILL.md
Instructions source · Aperçu en lecture seule
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.