cognitivecomputations
/

DeepSeek-R1-AWQ

Text Generation

4-bit precision

Model card Files Files and versions Community

Resources

View closed (15)

Add instructions to run R1-AWQ on SGLang

#22 opened about 3 hours ago by

requests get stuck when sending long prompts (already solved, but still don't know why?)

#18 opened 5 days ago by

Is there any accuracy results comparing to original DeepSeek-R1？

#15 opened 6 days ago by

Any one can run this model with SGlang framework？

#13 opened 7 days ago by

Regarding the issue of inconsistent calculation of tokens

#12 opened 13 days ago by

Max-Batch-Size, max-num-sequence, and fp_cache fp8_e4m3

#11 opened 13 days ago by

The inference performance of the DeepSeek-R1-AWQ model is weak compared to the DeepSeek-R1 model

#3 opened 20 days ago by