You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
cd deplopyment/docker_compose to cd deployment/docker_compose two times.
docker compose -f compose.yaml vllm-gaudi-server up -d to docker compose -f compose.yaml up vllm-gaudi-server -d
And:
Should we make a script parameter: VLLM_CPU_KVCACHE_SPACE=40 (line 43)? Can make it a little easier to change cache size depending on machine's memory.
Reproduce steps
Documentation only.
Raw log
Attachments
No response
The text was updated successfully, but these errors were encountered:
Priority
P4-Low
OS type
Ubuntu
Hardware type
Xeon-GNR
Installation method
Deploy method
Running nodes
Single Node
What's the version?
NA
Description
Small typos in comps/third_parties/vllm/README.md. Can change:
cd deplopyment/docker_compose
tocd deployment/docker_compose
two times.docker compose -f compose.yaml vllm-gaudi-server up -d
todocker compose -f compose.yaml up vllm-gaudi-server -d
And:
Reproduce steps
Documentation only.
Raw log
Attachments
No response
The text was updated successfully, but these errors were encountered: