issues
search
InftyAI
/
llmaz
☸️ Easy, advanced inference platform for large language models on Kubernetes
Apache License 2.0
13
stars
5
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Customized flags for backendRuntimes
#140
kerthcet
opened
4 hours ago
2
[2/N] Add backendRuntime implementation
#139
kerthcet
closed
52 minutes ago
2
[1/N] Add backendRuntime CRD
#138
kerthcet
closed
23 hours ago
3
helm chart support for easy installation
#137
kerthcet
opened
1 day ago
4
Fix resource limits could be small than requests
#136
kerthcet
closed
1 day ago
1
Add validation to Playground as the backendConfig's resource requests should not be greater than limits
#135
kerthcet
opened
1 day ago
1
Add new API object BackendRuntime for expandability
#134
kerthcet
closed
52 minutes ago
5
Support traditional models
#133
kerthcet
opened
2 days ago
1
Update typo
#132
kerthcet
closed
3 days ago
2
Update typo
#131
kerthcet
closed
3 days ago
2
Update Architecture
#130
kerthcet
closed
3 days ago
1
Add Architecture diagram
#129
kerthcet
closed
4 days ago
1
Bump vllm to 0.6.0 according to the great performance improvement
#128
kerthcet
opened
5 days ago
2
Prepare for v0.0.6
#127
kerthcet
closed
5 days ago
1
Prepare for v0.0.5
#126
kerthcet
closed
5 days ago
1
Change ModelClaims API
#125
kerthcet
closed
5 days ago
2
Add verbose log to modelLoader
#124
kerthcet
closed
6 days ago
1
Requests could be bigger than limits
#123
kerthcet
closed
1 day ago
2
Report filename and file size in modelLoader
#122
kerthcet
closed
6 days ago
3
[2/N] Support SpeculativeDecoding with llama.cpp
#121
kerthcet
closed
6 days ago
2
Add new conditions to Playground
#120
kerthcet
closed
6 days ago
2
Loading model weights more efficiently
#119
kerthcet
opened
1 week ago
2
[1/N] Add SpeculativeDecoding support
#118
kerthcet
closed
1 week ago
3
Add new status once models haven't been created
#117
kerthcet
closed
6 days ago
1
Bump github.com/onsi/gomega from 1.34.1 to 1.34.2
#116
dependabot[bot]
closed
1 week ago
2
Bump github.com/onsi/ginkgo/v2 from 2.20.1 to 2.20.2
#115
dependabot[bot]
closed
1 week ago
1
Unify the API routes for different inference engines
#114
kerthcet
closed
1 week ago
3
Add integration tests for Playground/Service status update
#113
kerthcet
closed
6 days ago
3
Add project logo
#112
kerthcet
closed
1 week ago
3
Add model label to Playground
#111
kerthcet
closed
1 week ago
2
update .github/PULL_REQUEST_TEMPLATE.md
#110
carlory
opened
1 week ago
4
Playground should be triggered to create Services and then Pods once the model is created
#109
carlory
closed
1 week ago
3
Fix watch for changes to LeaderWorkerSet created by llmaz and trigger a Reconcile for the owner
#108
carlory
closed
1 week ago
7
fix wrong field path in the openmodel webhook
#107
carlory
closed
2 weeks ago
2
Support scaling with Spot instances for cost saving
#106
kerthcet
opened
2 weeks ago
6
Bump github.com/onsi/ginkgo/v2 from 2.19.1 to 2.20.1
#105
dependabot[bot]
closed
2 weeks ago
1
Change model name to github.com/inftyai/llmaz
#104
kerthcet
closed
2 weeks ago
1
Accelerate model loading
#103
kerthcet
opened
2 weeks ago
2
Stop sharing model weights across Pods in the same node
#102
kerthcet
closed
2 weeks ago
1
Prepare for v0.0.4
#101
kerthcet
closed
3 weeks ago
1
Support filesystems
#100
kerthcet
opened
3 weeks ago
1
Download models in prior
#99
kerthcet
closed
2 weeks ago
3
Bump sigs.k8s.io/controller-runtime from 0.18.4 to 0.19.0
#98
dependabot[bot]
closed
3 weeks ago
1
Bump the kubernetes group with 5 updates
#97
dependabot[bot]
closed
3 weeks ago
1
Model aware scheduling
#96
kerthcet
opened
3 weeks ago
1
add e2e tests with llama.cpp
#95
kerthcet
closed
3 weeks ago
2
Support llama.cpp
#94
kerthcet
closed
3 weeks ago
2
Downsize the model-loader image
#93
kerthcet
opened
3 weeks ago
1
Playground will not reconcile once model created
#92
kerthcet
closed
1 week ago
2
ollama support
#91
kerthcet
opened
3 weeks ago
2
Next