Blue2Giant

Looking forward to the release of the dataset.

1

thanks for the sharing of your great job~ when would you release the dataset since noticing the plan in the todo list ?

vllm deployment model get stuck when processing api calls

4

```python (APIServer pid=704) INFO 10-31 04:37:39 [loggers.py:128] Engine 000: Avg prompt throughput: 11528.7 tokens/s, Avg generation throughput: 6.4 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%,...