[V1][Feature] Enable Speculative Decoding with Structured Outputs (#14702)

Signed-off-by: Benjamin Chislett <benjamin.chislett@centml.ai>
Signed-off-by: Benjamin Chislett <chislett.ben@gmail.com>
This commit is contained in:
Benjamin Chislett
2025-04-29 17:02:10 -07:00
committed by GitHub
parent 7489ec0bab
commit 34120f5acd
9 changed files with 207 additions and 57 deletions

View File

@@ -260,6 +260,7 @@ async def async_request_openai_completions(
if request_func_input.model_name else request_func_input.model,
"prompt": request_func_input.prompt,
"temperature": 0.0,
"repetition_penalty": 1.0,
"max_tokens": request_func_input.output_len,
"logprobs": request_func_input.logprobs,
"stream": True,