Skip to content
Merged
Changes from 1 commit
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions fastdeploy/entrypoints/openai/protocol.py
Original file line number Diff line number Diff line change
Expand Up @@ -548,6 +548,9 @@ class CompletionRequest(BaseModel):

collect_metrics: Optional[bool] = False

# NOTE(Wanglongzhi2001): temporary parameter for video understanding benchmark
video_fps: Optional[float] = None
Comment on lines +551 to +552
Copy link

Copilot AI Mar 30, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

当前 PR 标题使用了 [Other],但仓库 PR 模板的 tag list 中是 [Others](见 .github/pull_request_template.md 的 Checklist)。建议把标题 tag 调整为已有的 [Others] 或新增语义更明确的 tag,以满足仓库约定。

Copilot uses AI. Check for mistakes.

Comment on lines +551 to +553
Copy link

Copilot AI Mar 30, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

这里新增的 video_fps 目前只会被透传进 to_dict_for_infer() 的 req_dict,但在仓库内的输入处理链路中未找到任何地方读取/应用该字段(搜索仅在 protocol.py 中出现)。这会导致基准测试传入 video_fps 也不会影响实际抽帧逻辑。建议在预处理阶段将其映射到视频 item 的 fps(如 messages/multimodal_data 的 video part),或改为复用现有的 mm_processor_kwargs.video_fps 机制并在处理器侧消费该参数。

Copilot uses AI. Check for mistakes.
def to_dict_for_infer(self, request_id=None, prompt=None):
"""
Convert the request parameters into a dictionary
Expand Down Expand Up @@ -734,6 +737,9 @@ class ChatCompletionRequest(BaseModel):

collect_metrics: Optional[bool] = False

# NOTE(Wanglongzhi2001): temporary parameter for video understanding benchmark
video_fps: Optional[float] = None

Comment on lines +740 to +742
Copy link

Copilot AI Mar 30, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

新增请求字段后建议补充单测覆盖:例如验证当用户传入 video_fps 时,CompletionRequest/ChatCompletionRequest.to_dict_for_infer() 的输出会包含该字段(且为预期类型/取值)。仓库已有 openai protocol 相关测试(tests/entrypoints/openai/*),增加回归测试能避免后续重构导致该临时参数被悄然丢弃。

Copilot uses AI. Check for mistakes.
def to_dict_for_infer(self, request_id=None):
"""
Convert the request parameters into a dictionary
Expand Down
Loading