[PD] Fix large page size + chunk prefill (#5588)

This commit is contained in:
Byron Hsu
2025-04-20 17:21:54 -07:00
committed by GitHub
parent dcb8232596
commit c951d312ed
5 changed files with 37 additions and 6 deletions

View File

@@ -0,0 +1,13 @@
prompt = "Hello " * 16000
import json
import requests
response = requests.post(
"http://0.0.0.0:8000/generate",
json={"text": prompt, "sampling_params": {"temperature": 0}},
)
print("Response content (raw):", response.content)