ibm-ai-platform
/

llama3-8b-accelerator

Model card Files Files and versions

Resources

View closed (0)

Unexpectedly Large Memory Usage of ibm-fms/llama3-8b-accelerator in vLLM

#4 opened over 1 year ago by

llama3.1 version

#3 opened almost 2 years ago by

ValueError: Unsupported model type mlp_speculator using TGI server

#2 opened about 2 years ago by

rishabh-simpplr

shard 0 never ready when given the speculator option?

#1 opened about 2 years ago by