← Workflow
Optional · Step 0 · Quick check
Tensor Parallel Planner
Suggest TP/PP/EP split for a model on available GPUs.
Results
- Weight memory
- 32.0 GB
- Suggested TP
- 1
- Suggested PP
- 8
- Suggested EP (MoE)
- N/A (dense)
Optional step 0 — continue to Define workload (Lens) for the full platform workflow.