grpo中的async模式是否能够支持tensor_parallel_size>1 #3712

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Closed

kangyishuai opened this issue Mar 28, 2025 · 0 comments

Labels

kangyishuai commented Mar 28, 2025

举个例子：
可见显卡数量 = 8
训练显卡数量 = 6
推理显卡数量 = 2
tensor_parallel_size = 2
这样一个参数量大的模型或者token较长的模型才有足够的显存进行推理

hjh0119 added the enhancement label

hjh0119 mentioned this issue

Decouple vLLM engine and GRPOTrainer. #3911

Merged

4 tasks

hjh0119 closed this as completed

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment