Support VILA models (#6106)
This commit is contained in:
@@ -399,7 +399,7 @@ async def async_request_sglang_generate(
|
||||
# NOTE: Some completion API might have a last
|
||||
# usage summary response without a token so we
|
||||
# want to check a token was generated
|
||||
if data["text"]:
|
||||
if "text" in data and data["text"]:
|
||||
timestamp = time.perf_counter()
|
||||
generated_text = data["text"]
|
||||
output_len = data["meta_info"]["completion_tokens"]
|
||||
|
||||
Reference in New Issue
Block a user