mirror of
https://github.com/hanzo-ml/kserve.git
synced 2026-10-30 20:53:49 +00:00
Jagadeesh JandGitHub
55a3c4e5c8
* Feat: add huggingface bloom example to torchserve Signed-off-by: Jagadeesh J <[email protected]> * fix: add pv and helper pod yaml - update readme doc - add storageclass yaml - fix config.properties Signed-off-by: Jagadeesh J <[email protected]> * fix: add steps for model sharding
14 lines
569 B
Properties
14 lines
569 B
Properties
inference_address=http://0.0.0.0:8085
|
|
management_address=http://0.0.0.0:8085
|
|
metrics_address=http://0.0.0.0:8082
|
|
grpc_inference_port=7070
|
|
grpc_management_port=7071
|
|
enable_metrics_api=true
|
|
metrics_format=prometheus
|
|
number_of_netty_threads=4
|
|
job_queue_size=10
|
|
enable_envvars_config=true
|
|
install_py_dep_per_model=true
|
|
model_store=/mnt/models/model-store
|
|
model_snapshot={"name":"startup.cfg","modelCount":1,"models":{"bloom":{"1.0":{"defaultVersion":true,"marName":"bloom-560m.mar","minWorkers":1,"maxWorkers":5,"batchSize":1,"maxBatchDelay":5000,"responseTimeout":120}}}}
|