issues
search
substratusai
/
lingo
Lightweight ML model proxy and autoscaler for kubernetes
https://www.substratus.ai
Apache License 2.0
96
stars
6
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Flapping scale from 0 to 1 to 0 to 1
#67
samos123
closed
5 months ago
1
add leader election retry
#66
samos123
closed
5 months ago
3
Spike: Add integration test
#65
alpe
closed
4 months ago
1
Spike: Use retry middleware with reverse proxy
#64
alpe
closed
5 months ago
1
Customizable codebase
#63
nstogner
closed
5 months ago
2
Formatter, Linter and fixes
#62
alpe
opened
5 months ago
1
Retries - ReverseProxy.ErrorHandler based approach
#61
nstogner
closed
4 months ago
2
Lingo not leader even though there is only 1 replica after long pod uptime
#60
samos123
closed
5 months ago
5
Service name shouldn't have to match deployment name
#59
samos123
opened
5 months ago
9
Configure a default timeout of 30 minutes
#58
samos123
opened
5 months ago
2
Models endpoint
#57
nstogner
opened
5 months ago
0
Support Streaming
#56
nstogner
closed
3 months ago
2
Fix race condition in test
#55
alpe
closed
5 months ago
1
General housekeeping
#54
nstogner
closed
5 months ago
0
Race: make-race failing on local machine
#53
nstogner
closed
5 months ago
0
Spike: Configurable concurrency
#52
alpe
opened
6 months ago
0
Spike: Add optional retry middleware
#51
alpe
closed
5 months ago
1
Limit request queue to fail fast
#50
alpe
opened
6 months ago
1
Improve supply chain security
#49
alpe
opened
6 months ago
1
Lingo should retry on proxy failure
#48
nstogner
closed
4 months ago
3
Add diagrams
#47
nstogner
opened
6 months ago
1
Ensure deployment validity via admission hook
#46
alpe
opened
6 months ago
1
fix GHA to work for external contributors
#45
samos123
closed
6 months ago
0
Handle model undeployment
#44
alpe
closed
6 months ago
0
Add readiness endpoint
#43
alpe
closed
6 months ago
2
Handle model backend deployment deletions
#42
alpe
opened
6 months ago
2
Fine tuning backend limits
#41
alpe
closed
6 months ago
2
Add liveness, readiness probes to example deployment
#40
alpe
closed
6 months ago
1
Add Prometheus metrics
#39
alpe
closed
6 months ago
2
Better concurrent request handling for model host address
#38
alpe
closed
6 months ago
2
Batch (with buckets) Design
#37
nstogner
opened
6 months ago
1
Refactor towards sync.Map
#36
alpe
closed
6 months ago
1
fix #34 error scale from 0 to 1
#35
samos123
closed
7 months ago
1
error trying to scale after scaling up from 0 to 1
#34
samos123
closed
6 months ago
1
add ability to configure scale down delay
#33
samos123
closed
7 months ago
0
Configurable scale down time
#32
samos123
closed
7 months ago
0
Load tests
#31
nstogner
closed
7 months ago
0
Redeploying lingo causes deployments to get lost
#30
samos123
closed
7 months ago
2
WIP add batch inference test
#29
samos123
closed
7 months ago
1
HA with autoscaling
#28
nstogner
closed
7 months ago
0
remove flakiness from scale test
#27
samos123
closed
7 months ago
2
fix scale up after scaling to 0
#26
samos123
closed
7 months ago
0
Scale back to 0 and then scale up not working
#25
samos123
closed
7 months ago
0
Openai python system test and revert pr 19
#24
samos123
closed
8 months ago
0
Evaluate scenario: Dequeued and then cancelled
#23
samos123
closed
7 months ago
0
HTTP responses aren't closed and left open
#22
samos123
closed
7 months ago
8
add python openai multithread system test and fix hang in completeFunc
#21
samos123
closed
7 months ago
0
Package refactor
#20
nstogner
closed
7 months ago
0
Add queue cancellation on request cancellation
#19
nstogner
closed
8 months ago
2
Queue placement is not cancelled on request cancellation
#18
nstogner
closed
8 months ago
1
Previous
Next