SGLang 0.5.22
NVIDIA B300 x4 · tp4 × pp1- Speed per user (c=1)
- 118tok/s
- Time to first token
- 88ms
- Peak throughput
- 5,061tok/s @ 256
- Per GPU at peak
- 1,265tok/s
- Cold start
- 447s
- Context tested
- 8,192tokens
Measured 9 Nov 2026 · Throughput sweep
Measured 9 Nov 2026 · Throughput sweep
Measured 9 Nov 2026 · Throughput sweep
ModelPerf Pro