杨睿

Use panic recovery inside the eval goroutines, fix #79 .

fix: keep waiting if connection is not ready to close

3

related to https://github.com/encode/uvicorn/issues/111

Can't handle event type ConnectionClosed when role=SERVER and state=SEND_RESPONSE

1

Related to #111 #1636 may be a solution ## Reproducing ### 1. server code ```python import asyncio from fastapi import FastAPI, Request app = FastAPI() # !!!middleware is required to...

fix(automation): session is not created

4

## Problem Automation session is created when status changes from activate to completed through `store.UpsertAutomationSession(...)` api. It is not created when starting. So we **can not** get this session util...

## description After redis server reconnected, the redis lua script should be load again. ## log ```log File "/usr/local/lib/python3.10/site-packages/fastapi/dependencies/utils.py", line 543, in solve_dependencies solved = await call(**sub_values) File "/usr/local/lib/python3.10/site-packages/fastapi_limiter/depends.py", line...

[BUG] 计算 vision embedding 时没有凑batch，导致性能差

3

### 是否已有关于该错误的issue或讨论？ | Is there an existing issue / discussion for this? - [X] 我已经搜索过已有的issues和讨论 | I have searched the existing issues / discussions ### 该问题是否在FAQ中有解答？ | Is there an...

### Checklist Before Starting - [x] Search for similar PR(s). ### What does this PR do? - `max_tokens` is deprecated for vllm openai endpoint, use `max_completion_tokens` instead. - VLLM will...