EXP / 001
publisheddemo-runpile8/16/2026
Gemma 4 NVFP4 throughput optimization on RTX 5090
Checkpoint, concurrency, GPU rotation, KV-cache, and scheduler sweeps for a prefill-heavy binary-judge workload.
binary-judgegemma-4llm-inferenceprefill-heavyrtx-5090
- Runs
- 25
- Completed
- 23
- Failures
- 1
- Evidence
- 73