pmady/keda-gpu-scaler

Add ollama scaling profile about 3 hours ago

enhancement good first issue

92

KEDA External gRPC Scaler for GPU workloads - native NVML metrics via DaemonSet, no Prometheus required

Go

#ai-infrastructure#autoscaling#daemonset#gpu#gpu-autoscaling#gpu-metrics#gpu-monitoring#grpc#inference#keda#keda-external-scaler#keda-scalers#kubernetes#mlops#nvidia#nvml#prometheus#scale-to-zero#triton#vllm

Add parseMetadata unit tests for edge cases 7 days ago

good first issue testing

pmady/keda-gpu-scaler

92

KEDA External gRPC Scaler for GPU workloads - native NVML metrics via DaemonSet, no Prometheus required

Go

#ai-infrastructure#autoscaling#daemonset#gpu#gpu-autoscaling#gpu-metrics#gpu-monitoring#grpc#inference#keda#keda-external-scaler#keda-scalers#kubernetes#mlops#nvidia#nvml#prometheus#scale-to-zero#triton#vllm

UX: Contributor Onboarding Journey Map 7 days ago

good first issue ux contributor-experience

pmady/keda-gpu-scaler

92

KEDA External gRPC Scaler for GPU workloads - native NVML metrics via DaemonSet, no Prometheus required

Go

#ai-infrastructure#autoscaling#daemonset#gpu#gpu-autoscaling#gpu-metrics#gpu-monitoring#grpc#inference#keda#keda-external-scaler#keda-scalers#kubernetes#mlops#nvidia#nvml#prometheus#scale-to-zero#triton#vllm

UX: Fresh Eyes Walkthrough - First-Time User Experience Audit 7 days ago

documentation good first issue ux

pmady/keda-gpu-scaler

92

KEDA External gRPC Scaler for GPU workloads - native NVML metrics via DaemonSet, no Prometheus required

Go

#ai-infrastructure#autoscaling#daemonset#gpu#gpu-autoscaling#gpu-metrics#gpu-monitoring#grpc#inference#keda#keda-external-scaler#keda-scalers#kubernetes#mlops#nvidia#nvml#prometheus#scale-to-zero#triton#vllm

docs: add architecture diagram to README 8 days ago

documentation good first issue

pmady/keda-gpu-scaler

92

KEDA External gRPC Scaler for GPU workloads - native NVML metrics via DaemonSet, no Prometheus required

Go

#ai-infrastructure#autoscaling#daemonset#gpu#gpu-autoscaling#gpu-metrics#gpu-monitoring#grpc#inference#keda#keda-external-scaler#keda-scalers#kubernetes#mlops#nvidia#nvml#prometheus#scale-to-zero#triton#vllm

Add Terraform examples for AWS/GCP/Azure GPU node setup 8 days ago

documentation help wanted good first issue

pmady/keda-gpu-scaler

92

KEDA External gRPC Scaler for GPU workloads - native NVML metrics via DaemonSet, no Prometheus required

Go

#ai-infrastructure#autoscaling#daemonset#gpu#gpu-autoscaling#gpu-metrics#gpu-monitoring#grpc#inference#keda#keda-external-scaler#keda-scalers#kubernetes#mlops#nvidia#nvml#prometheus#scale-to-zero#triton#vllm

docs: populate ADOPTERS.md with real-world usage 10 days ago

documentation help wanted

pmady/keda-gpu-scaler

92

KEDA External gRPC Scaler for GPU workloads - native NVML metrics via DaemonSet, no Prometheus required

Go

#ai-infrastructure#autoscaling#daemonset#gpu#gpu-autoscaling#gpu-metrics#gpu-monitoring#grpc#inference#keda#keda-external-scaler#keda-scalers#kubernetes#mlops#nvidia#nvml#prometheus#scale-to-zero#triton#vllm

docs: improve Helm chart values.yaml documentation 10 days ago

documentation good first issue

pmady/keda-gpu-scaler

92

KEDA External gRPC Scaler for GPU workloads - native NVML metrics via DaemonSet, no Prometheus required

Go

#ai-infrastructure#autoscaling#daemonset#gpu#gpu-autoscaling#gpu-metrics#gpu-monitoring#grpc#inference#keda#keda-external-scaler#keda-scalers#kubernetes#mlops#nvidia#nvml#prometheus#scale-to-zero#triton#vllm

feat: add Triton Inference Server scaling profile 10 days ago

enhancement help wanted

pmady/keda-gpu-scaler

92

KEDA External gRPC Scaler for GPU workloads - native NVML metrics via DaemonSet, no Prometheus required

Go

#ai-infrastructure#autoscaling#daemonset#gpu#gpu-autoscaling#gpu-metrics#gpu-monitoring#grpc#inference#keda#keda-external-scaler#keda-scalers#kubernetes#mlops#nvidia#nvml#prometheus#scale-to-zero#triton#vllm

feat: add configurable cooldown to prevent scaling flap 10 days ago

enhancement help wanted

pmady/keda-gpu-scaler

92

KEDA External gRPC Scaler for GPU workloads - native NVML metrics via DaemonSet, no Prometheus required

Go

#ai-infrastructure#autoscaling#daemonset#gpu#gpu-autoscaling#gpu-metrics#gpu-monitoring#grpc#inference#keda#keda-external-scaler#keda-scalers#kubernetes#mlops#nvidia#nvml#prometheus#scale-to-zero#triton#vllm

feat: add health check endpoint to gRPC server 10 days ago

enhancement help wanted

pmady/keda-gpu-scaler

92

KEDA External gRPC Scaler for GPU workloads - native NVML metrics via DaemonSet, no Prometheus required

Go

#ai-infrastructure#autoscaling#daemonset#gpu#gpu-autoscaling#gpu-metrics#gpu-monitoring#grpc#inference#keda#keda-external-scaler#keda-scalers#kubernetes#mlops#nvidia#nvml#prometheus#scale-to-zero#triton#vllm

test: add table-driven tests for GPU metric aggregation 10 days ago

good first issue testing

pmady/keda-gpu-scaler

92

KEDA External gRPC Scaler for GPU workloads - native NVML metrics via DaemonSet, no Prometheus required

Go

#ai-infrastructure#autoscaling#daemonset#gpu#gpu-autoscaling#gpu-metrics#gpu-monitoring#grpc#inference#keda#keda-external-scaler#keda-scalers#kubernetes#mlops#nvidia#nvml#prometheus#scale-to-zero#triton#vllm

docs: add TROUBLESHOOTING.md for common issues 10 days ago

documentation good first issue

pmady/keda-gpu-scaler

92

KEDA External gRPC Scaler for GPU workloads - native NVML metrics via DaemonSet, no Prometheus required

Go

#ai-infrastructure#autoscaling#daemonset#gpu#gpu-autoscaling#gpu-metrics#gpu-monitoring#grpc#inference#keda#keda-external-scaler#keda-scalers#kubernetes#mlops#nvidia#nvml#prometheus#scale-to-zero#triton#vllm

Add golangci-lint config file 11 days ago

good first issue ci/cd

pmady/keda-gpu-scaler

92

KEDA External gRPC Scaler for GPU workloads - native NVML metrics via DaemonSet, no Prometheus required

Go

#ai-infrastructure#autoscaling#daemonset#gpu#gpu-autoscaling#gpu-metrics#gpu-monitoring#grpc#inference#keda#keda-external-scaler#keda-scalers#kubernetes#mlops#nvidia#nvml#prometheus#scale-to-zero#triton#vllm

New project: gpu-mcp-server - GPU metrics for AI agents via MCP 11 days ago

help wanted

pmady/keda-gpu-scaler

92

KEDA External gRPC Scaler for GPU workloads - native NVML metrics via DaemonSet, no Prometheus required

Go

#ai-infrastructure#autoscaling#daemonset#gpu#gpu-autoscaling#gpu-metrics#gpu-monitoring#grpc#inference#keda#keda-external-scaler#keda-scalers#kubernetes#mlops#nvidia#nvml#prometheus#scale-to-zero#triton#vllm

Add CI step to run go vet 13 days ago

good first issue ci/cd

pmady/keda-gpu-scaler

92

KEDA External gRPC Scaler for GPU workloads - native NVML metrics via DaemonSet, no Prometheus required

Go

#ai-infrastructure#autoscaling#daemonset#gpu#gpu-autoscaling#gpu-metrics#gpu-monitoring#grpc#inference#keda#keda-external-scaler#keda-scalers#kubernetes#mlops#nvidia#nvml#prometheus#scale-to-zero#triton#vllm

Add pre-commit hooks config 14 days ago

good first issue ci/cd

pmady/keda-gpu-scaler

92

KEDA External gRPC Scaler for GPU workloads - native NVML metrics via DaemonSet, no Prometheus required

Go

#ai-infrastructure#autoscaling#daemonset#gpu#gpu-autoscaling#gpu-metrics#gpu-monitoring#grpc#inference#keda#keda-external-scaler#keda-scalers#kubernetes#mlops#nvidia#nvml#prometheus#scale-to-zero#triton#vllm

Add gpu_name to scaler log messages 14 days ago

enhancement good first issue

pmady/keda-gpu-scaler

92

KEDA External gRPC Scaler for GPU workloads - native NVML metrics via DaemonSet, no Prometheus required

Go

#ai-infrastructure#autoscaling#daemonset#gpu#gpu-autoscaling#gpu-metrics#gpu-monitoring#grpc#inference#keda#keda-external-scaler#keda-scalers#kubernetes#mlops#nvidia#nvml#prometheus#scale-to-zero#triton#vllm

Add test coverage reporting to CI 14 days ago

good first issue ci/cd testing

pmady/keda-gpu-scaler

92

KEDA External gRPC Scaler for GPU workloads - native NVML metrics via DaemonSet, no Prometheus required

Go

#ai-infrastructure#autoscaling#daemonset#gpu#gpu-autoscaling#gpu-metrics#gpu-monitoring#grpc#inference#keda#keda-external-scaler#keda-scalers#kubernetes#mlops#nvidia#nvml#prometheus#scale-to-zero#triton#vllm

Add --dry-run flag to gpu-metrics CLI 14 days ago

enhancement good first issue

pmady/keda-gpu-scaler

92

KEDA External gRPC Scaler for GPU workloads - native NVML metrics via DaemonSet, no Prometheus required

Go

#ai-infrastructure#autoscaling#daemonset#gpu#gpu-autoscaling#gpu-metrics#gpu-monitoring#grpc#inference#keda#keda-external-scaler#keda-scalers#kubernetes#mlops#nvidia#nvml#prometheus#scale-to-zero#triton#vllm

Add CONTRIBUTORS.md 14 days ago

documentation good first issue

pmady/keda-gpu-scaler

92

KEDA External gRPC Scaler for GPU workloads - native NVML metrics via DaemonSet, no Prometheus required

Go

#ai-infrastructure#autoscaling#daemonset#gpu#gpu-autoscaling#gpu-metrics#gpu-monitoring#grpc#inference#keda#keda-external-scaler#keda-scalers#kubernetes#mlops#nvidia#nvml#prometheus#scale-to-zero#triton#vllm

Add p95 and p99 aggregation methods 14 days ago

enhancement help wanted

pmady/keda-gpu-scaler

92

KEDA External gRPC Scaler for GPU workloads - native NVML metrics via DaemonSet, no Prometheus required

Go

#ai-infrastructure#autoscaling#daemonset#gpu#gpu-autoscaling#gpu-metrics#gpu-monitoring#grpc#inference#keda#keda-external-scaler#keda-scalers#kubernetes#mlops#nvidia#nvml#prometheus#scale-to-zero#triton#vllm

Add GPU driver version to metrics output 14 days ago

enhancement good first issue

pmady/keda-gpu-scaler

92

KEDA External gRPC Scaler for GPU workloads - native NVML metrics via DaemonSet, no Prometheus required

Go

#ai-infrastructure#autoscaling#daemonset#gpu#gpu-autoscaling#gpu-metrics#gpu-monitoring#grpc#inference#keda#keda-external-scaler#keda-scalers#kubernetes#mlops#nvidia#nvml#prometheus#scale-to-zero#triton#vllm

Validate metricType values in parseMetadata 14 days ago

bug good first issue

pmady/keda-gpu-scaler

92

KEDA External gRPC Scaler for GPU workloads - native NVML metrics via DaemonSet, no Prometheus required

Go

#ai-infrastructure#autoscaling#daemonset#gpu#gpu-autoscaling#gpu-metrics#gpu-monitoring#grpc#inference#keda#keda-external-scaler#keda-scalers#kubernetes#mlops#nvidia#nvml#prometheus#scale-to-zero#triton#vllm

Add tgi-inference scaling profile for HuggingFace TGI 14 days ago

enhancement good first issue

pmady/keda-gpu-scaler

92

KEDA External gRPC Scaler for GPU workloads - native NVML metrics via DaemonSet, no Prometheus required

Go

#ai-infrastructure#autoscaling#daemonset#gpu#gpu-autoscaling#gpu-metrics#gpu-monitoring#grpc#inference#keda#keda-external-scaler#keda-scalers#kubernetes#mlops#nvidia#nvml#prometheus#scale-to-zero#triton#vllm

Add make fmt and make check-fmt targets 14 days ago

good first issue ci/cd

pmady/keda-gpu-scaler

92

KEDA External gRPC Scaler for GPU workloads - native NVML metrics via DaemonSet, no Prometheus required

Go

#ai-infrastructure#autoscaling#daemonset#gpu#gpu-autoscaling#gpu-metrics#gpu-monitoring#grpc#inference#keda#keda-external-scaler#keda-scalers#kubernetes#mlops#nvidia#nvml#prometheus#scale-to-zero#triton#vllm

Add --version flag to keda-gpu-scaler and gpu-metrics binaries 14 days ago

enhancement good first issue

pmady/keda-gpu-scaler

92

KEDA External gRPC Scaler for GPU workloads - native NVML metrics via DaemonSet, no Prometheus required

Go

#ai-infrastructure#autoscaling#daemonset#gpu#gpu-autoscaling#gpu-metrics#gpu-monitoring#grpc#inference#keda#keda-external-scaler#keda-scalers#kubernetes#mlops#nvidia#nvml#prometheus#scale-to-zero#triton#vllm

Add GitHub Actions CI with mock NVML tests 29 days ago

help wanted good first issue

pmady/keda-gpu-scaler

92

KEDA External gRPC Scaler for GPU workloads - native NVML metrics via DaemonSet, no Prometheus required

Go

#ai-infrastructure#autoscaling#daemonset#gpu#gpu-autoscaling#gpu-metrics#gpu-monitoring#grpc#inference#keda#keda-external-scaler#keda-scalers#kubernetes#mlops#nvidia#nvml#prometheus#scale-to-zero#triton#vllm

Add /healthz and /readyz endpoints for liveness/readiness probes about 1 month ago

enhancement help wanted good first issue

pmady/keda-gpu-scaler

92

KEDA External gRPC Scaler for GPU workloads - native NVML metrics via DaemonSet, no Prometheus required

Go

#ai-infrastructure#autoscaling#daemonset#gpu#gpu-autoscaling#gpu-metrics#gpu-monitoring#grpc#inference#keda#keda-external-scaler#keda-scalers#kubernetes#mlops#nvidia#nvml#prometheus#scale-to-zero#triton#vllm

Document all Helm chart values with descriptions about 1 month ago

documentation help wanted good first issue

pmady/keda-gpu-scaler

92

KEDA External gRPC Scaler for GPU workloads - native NVML metrics via DaemonSet, no Prometheus required

Go

#ai-infrastructure#autoscaling#daemonset#gpu#gpu-autoscaling#gpu-metrics#gpu-monitoring#grpc#inference#keda#keda-external-scaler#keda-scalers#kubernetes#mlops#nvidia#nvml#prometheus#scale-to-zero#triton#vllm

Add cloud-specific tutorials (GKE, EKS, AKS) with vLLM 3 months ago

documentation help wanted

pmady/keda-gpu-scaler

92

KEDA External gRPC Scaler for GPU workloads - native NVML metrics via DaemonSet, no Prometheus required

Go

#ai-infrastructure#autoscaling#daemonset#gpu#gpu-autoscaling#gpu-metrics#gpu-monitoring#grpc#inference#keda#keda-external-scaler#keda-scalers#kubernetes#mlops#nvidia#nvml#prometheus#scale-to-zero#triton#vllm

Add vLLM pending request queue depth as a scaling metric 3 months ago

enhancement help wanted

pmady/keda-gpu-scaler

92

KEDA External gRPC Scaler for GPU workloads - native NVML metrics via DaemonSet, no Prometheus required

Go

#ai-infrastructure#autoscaling#daemonset#gpu#gpu-autoscaling#gpu-metrics#gpu-monitoring#grpc#inference#keda#keda-external-scaler#keda-scalers#kubernetes#mlops#nvidia#nvml#prometheus#scale-to-zero#triton#vllm

Add end-to-end tests using mock GPU collector 3 months ago

good first issue

pmady/keda-gpu-scaler

92

KEDA External gRPC Scaler for GPU workloads - native NVML metrics via DaemonSet, no Prometheus required

Go

#ai-infrastructure#autoscaling#daemonset#gpu#gpu-autoscaling#gpu-metrics#gpu-monitoring#grpc#inference#keda#keda-external-scaler#keda-scalers#kubernetes#mlops#nvidia#nvml#prometheus#scale-to-zero#triton#vllm

Complete Helm chart and publish to Artifact Hub 3 months ago

enhancement help wanted

pmady/keda-gpu-scaler

92

KEDA External gRPC Scaler for GPU workloads - native NVML metrics via DaemonSet, no Prometheus required

Go

#ai-infrastructure#autoscaling#daemonset#gpu#gpu-autoscaling#gpu-metrics#gpu-monitoring#grpc#inference#keda#keda-external-scaler#keda-scalers#kubernetes#mlops#nvidia#nvml#prometheus#scale-to-zero#triton#vllm

Improve unit test coverage for edge cases and aggregation modes 3 months ago

good first issue

pmady/keda-gpu-scaler

92

KEDA External gRPC Scaler for GPU workloads - native NVML metrics via DaemonSet, no Prometheus required

Go

#ai-infrastructure#autoscaling#daemonset#gpu#gpu-autoscaling#gpu-metrics#gpu-monitoring#grpc#inference#keda#keda-external-scaler#keda-scalers#kubernetes#mlops#nvidia#nvml#prometheus#scale-to-zero#triton#vllm

Set up GitHub Actions release workflow with multi-arch Docker images 3 months ago

enhancement good first issue

pmady/keda-gpu-scaler

92

KEDA External gRPC Scaler for GPU workloads - native NVML metrics via DaemonSet, no Prometheus required

Go

#ai-infrastructure#autoscaling#daemonset#gpu#gpu-autoscaling#gpu-metrics#gpu-monitoring#grpc#inference#keda#keda-external-scaler#keda-scalers#kubernetes#mlops#nvidia#nvml#prometheus#scale-to-zero#triton#vllm

Add optional Prometheus metrics endpoint and Grafana dashboard 3 months ago

enhancement help wanted

pmady/keda-gpu-scaler

92

KEDA External gRPC Scaler for GPU workloads - native NVML metrics via DaemonSet, no Prometheus required

Go

#ai-infrastructure#autoscaling#daemonset#gpu#gpu-autoscaling#gpu-metrics#gpu-monitoring#grpc#inference#keda#keda-external-scaler#keda-scalers#kubernetes#mlops#nvidia#nvml#prometheus#scale-to-zero#triton#vllm

Replace ASCII diagram with SVG and add docker pull badge 3 months ago

documentation good first issue

pmady/keda-gpu-scaler

92

KEDA External gRPC Scaler for GPU workloads - native NVML metrics via DaemonSet, no Prometheus required

Go

#ai-infrastructure#autoscaling#daemonset#gpu#gpu-autoscaling#gpu-metrics#gpu-monitoring#grpc#inference#keda#keda-external-scaler#keda-scalers#kubernetes#mlops#nvidia#nvml#prometheus#scale-to-zero#triton#vllm

Add NVIDIA MIG (Multi-Instance GPU) per-instance metrics 3 months ago

enhancement help wanted

pmady/keda-gpu-scaler

92

KEDA External gRPC Scaler for GPU workloads - native NVML metrics via DaemonSet, no Prometheus required

Go

#ai-infrastructure#autoscaling#daemonset#gpu#gpu-autoscaling#gpu-metrics#gpu-monitoring#grpc#inference#keda#keda-external-scaler#keda-scalers#kubernetes#mlops#nvidia#nvml#prometheus#scale-to-zero#triton#vllm

Extract gpu.Collector interface for multi-vendor support 3 months ago

enhancement good first issue

pmady/keda-gpu-scaler

92

KEDA External gRPC Scaler for GPU workloads - native NVML metrics via DaemonSet, no Prometheus required

Go

#ai-infrastructure#autoscaling#daemonset#gpu#gpu-autoscaling#gpu-metrics#gpu-monitoring#grpc#inference#keda#keda-external-scaler#keda-scalers#kubernetes#mlops#nvidia#nvml#prometheus#scale-to-zero#triton#vllm

Add AMD ROCm GPU support via rocm-smi 3 months ago

enhancement help wanted

pmady/keda-gpu-scaler

92

KEDA External gRPC Scaler for GPU workloads - native NVML metrics via DaemonSet, no Prometheus required

Go

#ai-infrastructure#autoscaling#daemonset#gpu#gpu-autoscaling#gpu-metrics#gpu-monitoring#grpc#inference#keda#keda-external-scaler#keda-scalers#kubernetes#mlops#nvidia#nvml#prometheus#scale-to-zero#triton#vllm

Open Issues Need Help