sgl-project/DeepSeek-V4-Pro-FP8

🤗 On Hugging Facemit1599B params1.6 TBsafetensorsChecksums witnessedupdated today
Magnet

DeepSeek-V4-Pro-FP8

FP8 re-packaging of deepseek-ai/DeepSeek-V4-Pro.

Model architecture, tokenizer, chat template, and reference encoding/ are

unchanged from the base repo. No fine-tuning, no retraining — weights only.

Deployment

SGLang Cookbook: https://docs.sglang.io/cookbook/autoregressive/DeepSeek/DeepSeek-V4

License

MIT — see LICENSE. Copyright © DeepSeek.