Skip to content
This repository has been archived by the owner on Oct 11, 2024. It is now read-only.

Commit

Permalink
comment
Browse files Browse the repository at this point in the history
  • Loading branch information
@robertgshaw2-redhat
robertgshaw2-redhat committed Jun 25, 2024
1 parent cc24664 commit a8f701a
Showing 1 changed file with 1 addition and 1 deletion.
2 changes: 1 addition & 1 deletion tests/accuracy/test_lm_eval_correctness.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -76,7 +76,7 @@ def test_lm_eval_correctness(num_gpus_available):
"model": eval_config["model_name"],
"max-model-len": 4096,
"tensor-parallel-size": num_gpus_available,
# TODO: understand why default (mp) does not
# TODO (@robertgshaw2): understand why default (mp) does not
# shut down cleanly (it works, but not clean).
"distributed-executor-backend": "ray",
"disable-log-requests": "",
Expand Down

0 comments on commit a8f701a

Please sign in to comment.