16 lines
424 B
Markdown
16 lines
424 B
Markdown
# ADR-0003: Single-GPU first, multi-node ready
|
|
|
|
**Status:** Accepted
|
|
|
|
## Decision
|
|
|
|
Build the initial scheduler for one local NVIDIA GPU using Docker Compose and NVML, while keeping `ComputeNode` and `Accelerator` abstractions in the domain model.
|
|
|
|
## Rejected initially
|
|
|
|
- Kubernetes
|
|
- distributed inference scheduling
|
|
- multi-tenant cloud architecture
|
|
|
|
These add operational cost without solving the first product problem.
|