Tags: tmax-cloud/kserve
Tags
Fix failure to create gRPC isvc when specifying multiple ContainerPor… …ts (kserve#2464) * Fix failure to create gRPC isvc when specifying multiple ContainerPorts (kserve#2376) Signed-off-by: Andrews Arokiam <andrews.arokiam@ideas2it.com> * Update reconciler to add just svc Add grpc test for raw deployment Signed-off-by: Andrews Arokiam <andrews.arokiam@ideas2it.com> * Fix linting errors in test code Signed-off-by: Andrews Arokiam <andrews.arokiam@ideas2it.com> * Minor code improvements Signed-off-by: Dan Sun <dsun20@bloomberg.net> Signed-off-by: Andrews Arokiam <andrews.arokiam@ideas2it.com> Signed-off-by: Dan Sun <dsun20@bloomberg.net> Co-authored-by: Dan Sun <dsun20@bloomberg.net>
Start uvicorn server in multiple process as per worker count (kserve#… …2573) * start uvicorn server in multiple process as per worker count Signed-off-by: Suresh Nakkeran <suresh.n@ideas2it.com> * Add status code check for curl tests Signed-off-by: Dan Sun <dsun20@bloomberg.net> * Remove github token env Signed-off-by: Dan Sun <dsun20@bloomberg.net> * Add istio logs Signed-off-by: Dan Sun <dsun20@bloomberg.net> * Enable istio access log Signed-off-by: Dan Sun <dsun20@bloomberg.net> * print full logs Signed-off-by: Dan Sun <dsun20@bloomberg.net> * Set socket.SO_REUSEADDR Signed-off-by: Dan Sun <dsun20@bloomberg.net> * Fix mem limit Signed-off-by: Dan Sun <dsun20@bloomberg.net> * Enable grpc Signed-off-by: Dan Sun <dsun20@bloomberg.net> * fix custom predictor/transformer examples Signed-off-by: Dan Sun <dsun20@bloomberg.net> * Handle predictor call errors Signed-off-by: Dan Sun <dsun20@bloomberg.net>
Update configmap for helm chart v0.10.0-rc0 (kserve#2545) * Update configmap for helm chart v0.10.0-rc0 Signed-off-by: Dan Sun <dsun20@bloomberg.net> * Remove statefulset controller Signed-off-by: Dan Sun <dsun20@bloomberg.net> Signed-off-by: Dan Sun <dsun20@bloomberg.net>
Update 0.9.0-rc0 release manifest and github actions (kserve#2243) * Add router image publish github action Signed-off-by: Dan Sun <dsun20@bloomberg.net> * Fix model status test Signed-off-by: Dan Sun <dsun20@bloomberg.net> * Update isvc crd for autoscaling fields Signed-off-by: Dan Sun <dsun20@bloomberg.net> * Fix helm chart webhook configuration Signed-off-by: Dan Sun <dsun20@bloomberg.net> * Update modelmesh serving runtime crd Signed-off-by: Dan Sun <dsun20@bloomberg.net> * Use yaml variable for version Signed-off-by: Dan Sun <dsun20@bloomberg.net> * Add inferencegraphs rbac Signed-off-by: Dan Sun <dsun20@bloomberg.net> * Fix watcher test Signed-off-by: Dan Sun <dsun20@bloomberg.net>
Publish 0.8 release (kserve#2018) * Update pull request template Signed-off-by: Dan Sun <dsun20@bloomberg.net> * Publish v0.8.0 release Signed-off-by: Dan Sun <dsun20@bloomberg.net> * Add step to describe pods after e2e test failure Signed-off-by: Dan Sun <dsun20@bloomberg.net> * Set default install mode to Serverless Signed-off-by: Dan Sun <dsun20@bloomberg.net>
release: v0.8.0-rc0 (kserve#1989) Signed-off-by: Suresh Nakkeran <suresh.n@ideas2it.com>
Parallel inference support (kserve#1637) * Decouple http handler with KFModel * Add model type enum * Throw exception for unknown type * Implement model worker with RayServe deployment API * Add ray remote custom example * Update custom model server doc * Update custom model inference yaml * Check the model deployment type * Fix linting * Add local testing instruction * Fix image name * Reduce cpu resource
PreviousNext