Infrastructure●●Solid
Piqc – GPU waste scanner for LLM inference clusters
Read-only GPU waste scanner finds 20-40% cluster spend waste without agents or sidecars.
Solve My ProblemSlick
paralleliq
3024d ago
Back to browse
GitHub Repository
An open-source API Gateway & background daemon designed to queue inference surges and scale cloud GPUs down to zero when idle.
1 starsPython
ZeroGate – API gateway to scale cloud GPUs to zero when idle
by ngarner·Jun 26, 2026·2 points·0 comments
AI Analysis
●MidShip ItBold Bet
GPU autoscaling is solved by Kubernetes; this adds complexity without clear novelty.
Strengths
- •Mock mode tests orchestration logic without needing any actual GPU hardware accounts.
- •Integrated billing ledger tracks token-level utilization metrics alongside real-time infrastructure costs.
- •Docker Compose setup enables local evaluation of the full infrastructure stack immediately.
Weaknesses
- •Kubernetes KEDA already handles scale-to-zero autoscaling for any containerized workload universally.
- •Buzzword-heavy README obscures actual technical differentiation from existing established infrastructure tools.
Category
Target Audience
ML engineers managing multi-tenant inference pipelines
Similar To
Kubernetes KEDA · Skypilot · Modal
Similar Projects
AI/ML●●Solid
Piqc – An open-source GPU waste scanner for LLM inference clusters
One-command GPU waste scanner when Kubecost requires full Prometheus setup.
Solve My ProblemNiche Gem
samhoss93
1121d ago
Developer Tools●●Solid
Gpu.fund, live GPU cloud rental prices
Finally a single tab to check H100 prices instead of opening ten provider dashboards.
Solve My ProblemShip It
justacatbot
411mo ago
AI/ML●Mid
I reduced LLM inference GPU calls by 94% using semantic routing
94% GPU reduction claim needs verifiable benchmarks to stand out.
Bold BetShip It
kanacki
2124d ago
Infrastructure●●Solid
LLM-Gateway – Zero-Trust LLM Gateway
Zero-trust networking via zrok beats LiteLLM when your GPUs sit behind NAT.
Big BrainSolve My Problem
michaelquigley
713mo ago
Finance●●Solid
Open-source GPU cost analysis tool
Detects idle L40S nodes and oversized SageMaker endpoints to cut AWS GPU spend.
Solve My ProblemShip It
maksimov
101mo ago