Mirrors
/
hf_text-generation-inference
mirror of https://github.com/huggingface/text-generation-inference.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

0.4.0

This commit is contained in:
OlivierDehaene 2023-03-12 10:06:15 +01:00
parent c01d9b9d99
commit 47ac334a21
1 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
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-4e685d9 image: db4c2190dd824d1f950f5d1555fbadf0.azurecr.io/text-generation-inference:0.4.0
inference_config: inference_config:
liveness_route: liveness_route:
port: 80 port: 80
@ -24,14 +24,14 @@ 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: 200 initial_delay: 90
timeout: 60 timeout: 20
period: 60 period: 60
success_threshold: 1 success_threshold: 1
failure_threshold: 2 failure_threshold: 2
readiness_probe: readiness_probe:
initial_delay: 200 initial_delay: 90
timeout: 60 timeout: 20
period: 60 period: 60
success_threshold: 1 success_threshold: 1
failure_threshold: 2 failure_threshold: 2