huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-04-21 23:12:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

update probes

Browse Source
This commit is contained in:
OlivierDehaene 2023-03-09 09:52:11 +01:00
parent f067673a1d
commit c3e2b79a9e
1 changed files with 7 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
aml/deployment.yaml
View File

@ -8,7 +8,7 @@ environment_variables:
MODEL_ID: bigscience/bloom MODEL_ID: bigscience/bloom
NUM_SHARD: 8 NUM_SHARD: 8
environment: environment:
image: db4c2190dd824d1f950f5d1555fbadf0.azurecr.io/text-generation-inference:sha-cd5961b image: db4c2190dd824d1f950f5d1555fbadf0.azurecr.io/text-generation-inference:sha-941cd42
inference_config: inference_config:
liveness_route: liveness_route:
port: 80 port: 80
@ -24,15 +24,15 @@ request_settings:
request_timeout_ms: 60000 request_timeout_ms: 60000
max_concurrent_requests_per_instance: 256 max_concurrent_requests_per_instance: 256
liveness_probe: liveness_probe:
initial_delay: 140 initial_delay: 200
timeout: 60 timeout: 20
period: 60 period: 60
success_threshold: 1 success_threshold: 1
failure_threshold: 2 failure_threshold: 5
readiness_probe: readiness_probe:
initial_delay: 140 initial_delay: 200
timeout: 60 timeout: 20
period: 60 period: 60
success_threshold: 1 success_threshold: 1
failure_threshold: 2 failure_threshold: 5
instance_count: 1 instance_count: 1