sglangv0.5.2 & support Qwen3-Next-80B-A3B-Instruct

This commit is contained in:
maxiao1
2025-09-13 17:00:20 +08:00
commit 118f1fc726
2037 changed files with 515371 additions and 0 deletions

View File

@@ -0,0 +1,22 @@
prompt = "The capital of france is "
import json
import requests
response = requests.post(
"http://0.0.0.0:8000/generate",
json={
"text": prompt,
"sampling_params": {"temperature": 0},
"return_logprob": True,
"return_input_logprob": True,
"logprob_start_len": 0,
},
)
j = response.json()
input_logprobs = j["meta_info"]["input_token_logprobs"]
output_logprobs = j["meta_info"]["output_token_logprobs"]
print(len(input_logprobs), len(output_logprobs))