huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-06-19 15:52:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

revert aml changes

Browse Source
This commit is contained in:
OlivierDehaene 2023-03-30 15:02:08 +02:00
parent 163c23f174
commit 3a0e706346
1 changed files with 11 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
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:0.4.0 image: db4c2190dd824d1f950f5d1555fbadf0.azurecr.io/text-generation-inference:0.2.0
inference_config: inference_config:
liveness_route: liveness_route:
port: 80 port: 80
@ -18,21 +18,21 @@ environment:
path: /health path: /health
scoring_route: scoring_route:
port: 80 port: 80
path: / path: /generate
instance_type: Standard_ND96amsr_A100_v4 instance_type: Standard_ND96amsr_A100_v4
request_settings: request_settings:
request_timeout_ms: 60000 request_timeout_ms: 90000
max_concurrent_requests_per_instance: 256 max_concurrent_requests_per_instance: 256
liveness_probe: liveness_probe:
initial_delay: 90 initial_delay: 600
timeout: 20 timeout: 90
period: 60 period: 120
success_threshold: 1 success_threshold: 1
failure_threshold: 2 failure_threshold: 5
readiness_probe: readiness_probe:
initial_delay: 90 initial_delay: 600
timeout: 60 timeout: 90
period: 60 period: 120
success_threshold: 1 success_threshold: 1
failure_threshold: 2 failure_threshold: 5
instance_count: 1 instance_count: 1