Skip to content

update default paths and disable offloading for AMD qwen3-4B training #1225

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
zhuzilin merged 2 commits into from
Jan 5, 2026
Merged

update default paths and disable offloading for AMD qwen3-4B training #1225

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
ba44850
update default paths and disable offloading for AMD qwen3-4B training
Vivicai1005 Dec 26, 2025
644167c
Merge branch 'main' into amd-example
Vivicai1005 Jan 5, 2026
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
8 changes: 5 additions & 3 deletions scripts/run-qwen3-4B-amd.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,13 +15,13 @@ set -euxo pipefail


### AMD Support ###
SLIME_DIR="${SLIME_DIR:-/home/yushensu/projects/slime}" # Default path if not set in environment
SLIME_DIR="${SLIME_DIR:-/root}" # Default path if not set in environment
export SLIME_DIR

MODEL_DIR="${MODEL_DIR:-/home/yushensu/projects/model}" # Default path if not set in environment
MODEL_DIR="${MODEL_DIR:-/root}" # Default path if not set in environment
export MODEL_DIR

DATA_DIR="${DATA_DIR:-/home/yushensu/projects/data}" # Default path if not set in environment
DATA_DIR="${DATA_DIR:-/root}" # Default path if not set in environment
export DATA_DIR

# For AMD GPU
Expand Down Expand Up @@ -153,6 +153,8 @@ ray job submit --address="http://127.0.0.1:8265" \
--actor-num-nodes 1 \
--actor-num-gpus-per-node 8 \
--colocate \
--no-offload-train \
--no-offload-rollout \
${MODEL_ARGS[@]} \
${CKPT_ARGS[@]} \
${ROLLOUT_ARGS[@]} \
Expand Down