280 B
280 B
vllm-dspark Benchmark Grid Report
- Result root:
/data/user1/yy/bench_results/eagle_grid - Model:
/data/models/DeepSeek-V4-Flash-DSpark - Backend: vllm-dspark (TP=8, FP8 KV cache, spec-method=dspark, spec-tokens=5)
- Benchmark client:
sglang.bench_serving --backend vllm