【feature】support n parameter #4273
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Thanks for your contribution! |
|
|
luukunn
reviewed
Sep 28, 2025
| request["prompt_token_ids_len"] = len(request["prompt_token_ids"]) | ||
| input_ids_len = request["prompt_token_ids_len"] | ||
| request["max_tokens"] = min(self.max_model_len - input_ids_len, request.get("max_tokens")) | ||
| if request.get("reasoning_max_tokens", None) is None: |
There was a problem hiding this comment.
这里reasoning_max_tokens的逻辑去掉吧
| chunk_object_type: str = "chat.completion.chunk" | ||
| first_iteration = True | ||
| previous_num_tokens = 0 | ||
| n_param = request.n if request.n is not None else 1 |
There was a problem hiding this comment.
直接用num_choices就可以，不用再加一个n_param，
| first_iteration[idx] = False | ||
|
|
||
| output = res["outputs"] | ||
| reasoning_content = output["reasoning_content"] |
|
|
||
| delta_message = DeltaMessage( | ||
| reasoning_content="", | ||
| reasoning_content=reasoning_content, |
There was a problem hiding this comment.
这行也改成reasoning_content=""
| prompt_tokens_details=PromptTokenUsageInfo(cached_tokens=final_res.get("num_cached_tokens", 0)), | ||
| prompt_tokens_details=PromptTokenUsageInfo(cached_tokens=sum(num_cached_tokens)), | ||
| ) | ||
| work_process_metrics.e2e_request_latency.observe(time.time() - final_res["metrics"]["request_start_time"]) |
| request_prompts = request_prompt_ids | ||
|
|
||
| num_choices = len(request_prompts) | ||
| num_choices = len(request_prompts) * request.n |
There was a problem hiding this comment.
request.n需要判空，下面的n_param = current_req_dict.get("n", 1)可以挪到上面来，用n_param去乘
| try: | ||
| for idx, prompt in enumerate(request_prompts): | ||
| request_id_idx = f"{request_id}-{idx}" | ||
| request_id_idx = f"{request_id}" |
| for idx, prompt in enumerate(request_prompts): | ||
| request_id_idx = f"{request_id}-{idx}" | ||
| request_id_idx = f"{request_id}" | ||
| current_req_dict = request.to_dict_for_infer(request_id_idx, prompt) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Support adding the parameter
nto the request to retrieve multiple model responses.