NVIDIA-NeMo / NVIDIA-NeMo/RL

Avoid vLLM copy (doubles the memory)

Open
#72 1 comment 0 reactions 3 assignees Claimed by @yuki-97 View on GitHub
inference Performance vllm
Dominant language
Python
Stars
2k
Forks
561
Avg merge
4d 5h
Merged PRs (30d)
145

Description

When vLLM wakes up it uses memory and the cuda IPC also uses memory

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.