@@ -1947,18 +1947,17 @@ <h2 id="model-setup">Model Setup</h2>
19471947</ div >
19481948< h3 id ="deploy-sample-models "> Deploy Sample Models</ h3 >
19491949< h4 id ="simulator-model-cpu "> Simulator Model (CPU)</ h4 >
1950+ < p > A lightweight mock service for testing that generates responses without running an actual language model.</ p >
19501951< div class ="highlight "> < pre > < span > </ span > < code > < a id ="__codelineno-2-1 " name ="__codelineno-2-1 " href ="#__codelineno-2-1 "> </ a > < span class ="nv "> PROJECT_DIR</ span > < span class ="o "> =</ span > < span class ="k "> $(</ span > git< span class ="w "> </ span > rev-parse< span class ="w "> </ span > --show-toplevel< span class ="k "> )</ span >
19511952< a id ="__codelineno-2-2 " name ="__codelineno-2-2 " href ="#__codelineno-2-2 "> </ a > kustomize< span class ="w "> </ span > build< span class ="w "> </ span > < span class ="si "> ${</ span > < span class ="nv "> PROJECT_DIR</ span > < span class ="si "> }</ span > /docs/samples/models/simulator/< span class ="w "> </ span > < span class ="p "> |</ span > < span class ="w "> </ span > kubectl< span class ="w "> </ span > apply< span class ="w "> </ span > -f< span class ="w "> </ span > -
19521953</ code > </ pre > </ div >
19531954< h4 id ="facebook-opt-125m-model-cpu "> Facebook OPT-125M Model (CPU)</ h4 >
1955+ < p > An inference deployment that loads and runs a 125M parameter model without the need for a GPU.</ p >
19541956< div class ="highlight "> < pre > < span > </ span > < code > < a id ="__codelineno-3-1 " name ="__codelineno-3-1 " href ="#__codelineno-3-1 "> </ a > < span class ="nv "> PROJECT_DIR</ span > < span class ="o "> =</ span > < span class ="k "> $(</ span > git< span class ="w "> </ span > rev-parse< span class ="w "> </ span > --show-toplevel< span class ="k "> )</ span >
19551957< a id ="__codelineno-3-2 " name ="__codelineno-3-2 " href ="#__codelineno-3-2 "> </ a > kustomize< span class ="w "> </ span > build< span class ="w "> </ span > < span class ="si "> ${</ span > < span class ="nv "> PROJECT_DIR</ span > < span class ="si "> }</ span > /docs/samples/models/facebook-opt-125m-cpu/< span class ="w "> </ span > < span class ="p "> |</ span > < span class ="w "> </ span > kubectl< span class ="w "> </ span > apply< span class ="w "> </ span > -f< span class ="w "> </ span > -
19561958</ code > </ pre > </ div >
19571959< h4 id ="qwen3-model-gpu-required "> Qwen3 Model (GPU Required)</ h4 >
1958- < div class ="admonition warning ">
1959- < p class ="admonition-title "> Warning</ p >
1960- < p > This model requires GPU nodes with < code > nvidia.com/gpu</ code > resources available in your cluster.</ p >
1961- </ div >
1960+ < p > ⚠️ This model requires GPU nodes with < code > nvidia.com/gpu</ code > resources available in your cluster.</ p >
19621961< div class ="highlight "> < pre > < span > </ span > < code > < a id ="__codelineno-4-1 " name ="__codelineno-4-1 " href ="#__codelineno-4-1 "> </ a > < span class ="nv "> PROJECT_DIR</ span > < span class ="o "> =</ span > < span class ="k "> $(</ span > git< span class ="w "> </ span > rev-parse< span class ="w "> </ span > --show-toplevel< span class ="k "> )</ span >
19631962< a id ="__codelineno-4-2 " name ="__codelineno-4-2 " href ="#__codelineno-4-2 "> </ a > kustomize< span class ="w "> </ span > build< span class ="w "> </ span > < span class ="si "> ${</ span > < span class ="nv "> PROJECT_DIR</ span > < span class ="si "> }</ span > /docs/samples/models/qwen3/< span class ="w "> </ span > < span class ="p "> |</ span > < span class ="w "> </ span > kubectl< span class ="w "> </ span > apply< span class ="w "> </ span > -f< span class ="w "> </ span > -
19641963</ code > </ pre > </ div >
@@ -2016,7 +2015,7 @@ <h2 id="next-steps">Next Steps</h2>
20162015 < span class ="md-icon " title ="Last update ">
20172016 < svg xmlns ="http://www.w3.org/2000/svg " viewBox ="0 0 24 24 "> < path d ="M21 13.1c-.1 0-.3.1-.4.2l-1 1 2.1 2.1 1-1c.2-.2.2-.6 0-.8l-1.3-1.3c-.1-.1-.2-.2-.4-.2m-1.9 1.8-6.1 6V23h2.1l6.1-6.1zM12.5 7v5.2l4 2.4-1 1L11 13V7zM11 21.9c-5.1-.5-9-4.8-9-9.9C2 6.5 6.5 2 12 2c5.3 0 9.6 4.1 10 9.3-.3-.1-.6-.2-1-.2s-.7.1-1 .2C19.6 7.2 16.2 4 12 4c-4.4 0-8 3.6-8 8 0 4.1 3.1 7.5 7.1 7.9l-.1.2z "/> </ svg >
20182017 </ span >
2019- < span class ="git-revision-date-localized-plugin git-revision-date-localized-plugin-date " title ="February 10 , 2026 14:30:13 UTC "> February 10 , 2026</ span >
2018+ < span class ="git-revision-date-localized-plugin git-revision-date-localized-plugin-date " title ="March 3 , 2026 21:54:05 UTC "> March 3 , 2026</ span >
20202019 </ span >
20212020
20222021
0 commit comments