🎯
Focusing
Creator of KubeAI, a K8s operator to serve LLMs in production.
- San Francisco Bay Area
- https://www.kubeai.org/
- in/samstoelinga
Pinned Loading
-
substratusai/kubeai
substratusai/kubeai PublicAI Inference Operator for Kubernetes. The easiest way to serve ML models in production. Supports VLMs, LLMs, embeddings, and speech-to-text.
-
websu-io/websu
websu-io/websu PublicWebsite Speed and Performance Optimization and monitoring
-
docker-veth
docker-veth Publicshow which veth interface is associated with each container
-
docker-drupal
docker-drupal PublicDrupal image based official php image, database information should be passed by environment variables or linked container. Drush is included
-
-
chatgpt-blog
chatgpt-blog PublicPrototype using chatGPT to anser Golang Stackoverflow questions
874 contributions in the last year
Day of Week | April Apr | May May | June Jun | July Jul | August Aug | September Sep | October Oct | November Nov | December Dec | January Jan | February Feb | March Mar | |||||||||||||||||||||||||||||||||||||||||
Sunday Sun | |||||||||||||||||||||||||||||||||||||||||||||||||||||
Monday Mon | |||||||||||||||||||||||||||||||||||||||||||||||||||||
Tuesday Tue | |||||||||||||||||||||||||||||||||||||||||||||||||||||
Wednesday Wed | |||||||||||||||||||||||||||||||||||||||||||||||||||||
Thursday Thu | |||||||||||||||||||||||||||||||||||||||||||||||||||||
Friday Fri | |||||||||||||||||||||||||||||||||||||||||||||||||||||
Saturday Sat |
Less
No contributions.
Low contributions.
Medium-low contributions.
Medium-high contributions.
High contributions.
More
Contribution activity
March 2025
Created 33 commits in 4 repositories
Created 3 repositories
-
samos123/axlearn-aid
Shell
This contribution was made on Mar 29
-
samos123/Awesome-LLMOps
Shell
This contribution was made on Mar 25
-
samos123/HighPerfLLMs2024
Python
This contribution was made on Mar 7
Opened 17 pull requests in 3 repositories
substratusai/kubeai
3
open
10
merged
2
closed
-
wip: add kafka doc
This contribution was made on Mar 28
-
update vLLM GH200 image to 0.8.2
This contribution was made on Mar 28
-
bump helm chart versions
This contribution was made on Mar 26
-
add gemma 3 12b and 24b ollama on l4
This contribution was made on Mar 26
-
update vllm to 0.8.2
This contribution was made on Mar 26
-
wip update vLLM GH200 image to 0.8.1
This contribution was made on Mar 26
-
Add model mistral 3.1 small on 1x H100
This contribution was made on Mar 21
-
update vLLM image for GPU to 0.8.1
This contribution was made on Mar 20
-
bump helm chart versions
This contribution was made on Mar 16
-
Infinity engine e2e test
This contribution was made on Mar 13
-
simplify rollouts and fix old pod not getting deleted
This contribution was made on Mar 8
-
Support changing URL when cacheProfile is used
This contribution was made on Mar 5
-
add goatcounter analytics to kubeai.org website
This contribution was made on Mar 4
-
bump helm chart versions
This contribution was made on Mar 4
-
Url mutable with cache profile
This contribution was made on Mar 1
substratusai/vllm-docker
1
merged
-
Add image for Gh200
This contribution was made on Mar 28
tensorchord/Awesome-LLMOps
1
merged
-
Add KubeAI
This contribution was made on Mar 25
Reviewed 17 pull requests in 3 repositories
substratusai/kubeai
14 pull requests
-
fix: use correct accessKeyID values in if statement
This contribution was made on Mar 28
-
fix: support accessing models from private S3 buckets
This contribution was made on Mar 26
-
Add AKS installation guide
This contribution was made on Mar 25
-
fix: Include minReplicas even when value is 0
This contribution was made on Mar 25
-
WIP Proposal: Multi-spec Models
This contribution was made on Mar 24
-
Strongly typed OpenAI payloads
This contribution was made on Mar 18
-
E2e test updates
This contribution was made on Mar 18
-
Ollama load model from PVC
This contribution was made on Mar 13
-
Add sticky session section to paper
This contribution was made on Mar 5
-
add goatcounter analytics to kubeai.org website
This contribution was made on Mar 4
-
Add .spec.files to Model
This contribution was made on Mar 4
-
Make url mutable when cacheProfile is not used
This contribution was made on Mar 2
-
Update arch diagram
This contribution was made on Mar 2
-
Update to readme
This contribution was made on Mar 1
apple/axlearn
2 pull requests
-
use "true" and "false" instead of 0 and 1
This contribution was made on Mar 29
-
Add GKE A3 Ultra support
This contribution was made on Mar 7
GoogleCloudPlatform/ml-auto-solutions
1 pull request
-
Added project_bite_tpu_unittests and associated config to test axlear…
This contribution was made on Mar 5
Created an issue in substratusai/kubeai that received 2 comments
CPU and GPU Hybrid Mode: Hot Ollama with CPU and cold vLLM for GPU
Use case: GPUs are expensive and don't need them 24/7 however TTFT needs to stay low for cold starts. Example for Llama 3.3 70B: Ollama with CPU a…
2
comments
Opened 3 other issues in 1 repository
substratusai/kubeai
3
open
-
vLLM: Disaggregated Serving support
This contribution was made on Mar 21
-
LoRA Adapters from S3 Compatible Storage Server
This contribution was made on Mar 8
-
Add doc that explains how rollouts are handled
This contribution was made on Mar 2