Skip to content

fix(verl): disable vllm compile cache to work around corruption bug #490

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

Merged
jeffreysijuntan merged 1 commit into from
Apr 6, 2026
Merged

fix(verl): disable vllm compile cache to work around corruption bug #490

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
4 changes: 3 additions & 1 deletion rllm/trainer/verl/ray_runtime_env.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,9 @@
"VLLM_LOGGING_LEVEL": "WARN",
"VLLM_ALLOW_RUNTIME_LORA_UPDATING": "true",
"CUDA_DEVICE_MAX_CONNECTIONS": "1",
"VLLM_USE_V1": "1",
# TODO: disable compile cache due to cache corruption issue
# https://github.com/vllm-project/vllm/issues/31199
"VLLM_DISABLE_COMPILE_CACHE": "1",
# To prevent hanging or crash during synchronization of weights between actor and rollout
# in disaggregated mode. See:
# https://docs.vllm.ai/en/latest/usage/troubleshooting.html?h=nccl_cumem_enable#known-issues
Expand Down
Loading