search

Franc-Z / QWen1.5_TensorRT-LLM

Optimize QWen1.5 models with TensorRT-LLM
Apache License 2.0
15 stars 3 forks source link

mpirun with wrong world size in README.md #5

Open ywx217 opened 3 months ago

ywx217 commented 3 months ago

In README.md, Run the engines section, the TP=4 example uses 4 GPUs, but the process count in mpirun argument is -n 2.

Is this correct?