README.md

metadata

license: mit
language:
  - en
  - zh
base_model:
  - deepseek-ai/DeepSeek-R1
pipeline_tag: text-generation
library_name: transformers

DeepSeek R1 AWQ

AWQ of the DeepSeek R1 model.

This quant modified some of the model code to fix the overflow issue when using float16.

Tested on vLLM with 8x H100, inference speed 5 tokens per second with batch size 1 and short prompt, 12 tokens per second when using moe_wna16 kernel.

If you are serving with vLLM, please either add --dtype float16 or use the new moe_wna16 kernel by using --quantization moe_wna16.