List your company

Streaming Inference on OHLCV (155–925 samples)

43.4Average Latency (ms)LayerScale
-113.344944.6782,002.73,060.722May 13, 2026

Evaluation results

MethodLinks
LayerScale2026.0543.453.3—
SGLang2026.05105.653.32.4
vLLM2026.05139.153.33.2
TensorRT-LLM2026.05228.853.35.3
llama.cppcaching=enabled2026.0525446.75.9
GPT-3.5-Turbo2026.059267521
GPT-4o-mini2026.051,1245526
Claude 3.5 Sonnet2026.052,6287061
Claude 3.5 Haiku2026.053,9626592