neuralmagic
/

DeepSeek-Coder-V2-Instruct-FP8

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Quantize DeepSeek-Coder-V2-Instruct to W8A8(INT8)?

#2

by traphix - opened Aug 21

traphix

Aug 21

Because Ampere does not support fp8. So, any plan to quantize DeepSeek-Coder-V2-Instruct to W8A8(INT8)?

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment