mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-04-21 23:12:07 +00:00
v0.2.0
This commit is contained in:
parent
e114d87486
commit
80d03723a7
@ -21,18 +21,18 @@ environment:
|
|||||||
path: /generate
|
path: /generate
|
||||||
instance_type: Standard_ND96amsr_A100_v4
|
instance_type: Standard_ND96amsr_A100_v4
|
||||||
request_settings:
|
request_settings:
|
||||||
request_timeout_ms: 90000
|
request_timeout_ms: 60000
|
||||||
max_concurrent_requests_per_instance: 256
|
max_concurrent_requests_per_instance: 256
|
||||||
liveness_probe:
|
liveness_probe:
|
||||||
initial_delay: 600
|
initial_delay: 80
|
||||||
timeout: 90
|
timeout: 60
|
||||||
period: 120
|
period: 60
|
||||||
success_threshold: 1
|
success_threshold: 1
|
||||||
failure_threshold: 5
|
failure_threshold: 2
|
||||||
readiness_probe:
|
readiness_probe:
|
||||||
initial_delay: 600
|
initial_delay: 80
|
||||||
timeout: 90
|
timeout: 60
|
||||||
period: 120
|
period: 60
|
||||||
success_threshold: 1
|
success_threshold: 1
|
||||||
failure_threshold: 5
|
failure_threshold: 2
|
||||||
instance_count: 1
|
instance_count: 1
|
||||||
|
Loading…
Reference in New Issue
Block a user