Unverified Commit 910d74f5 authored by Ryan McCormick's avatar Ryan McCormick Committed by GitHub
Browse files

fix: Add mpi arg to all srun commands (#5948)

parent 16956ac6
...@@ -41,6 +41,7 @@ fi ...@@ -41,6 +41,7 @@ fi
# the stdout/stderr to files. # the stdout/stderr to files.
echo "Launching frontend services in background." echo "Launching frontend services in background."
srun \ srun \
--mpi pmix \
--overlap \ --overlap \
--container-image "${IMAGE}" \ --container-image "${IMAGE}" \
--container-mounts "${MOUNTS}" \ --container-mounts "${MOUNTS}" \
...@@ -71,4 +72,4 @@ srun \ ...@@ -71,4 +72,4 @@ srun \
--nodes "${NUM_NODES}" \ --nodes "${NUM_NODES}" \
--ntasks-per-node "${NUM_GPUS_PER_NODE}" \ --ntasks-per-node "${NUM_GPUS_PER_NODE}" \
--jobid "${SLURM_JOB_ID}" \ --jobid "${SLURM_JOB_ID}" \
/mnt/examples/basics/multinode/trtllm/start_trtllm_worker.sh & /mnt/examples/basics/multinode/trtllm/start_trtllm_worker.sh &
\ No newline at end of file
...@@ -44,6 +44,7 @@ fi ...@@ -44,6 +44,7 @@ fi
# the stdout/stderr to files. # the stdout/stderr to files.
echo "Launching frontend services in background." echo "Launching frontend services in background."
srun \ srun \
--mpi pmix \
--overlap \ --overlap \
--container-image "${IMAGE}" \ --container-image "${IMAGE}" \
--container-mounts "${MOUNTS}" \ --container-mounts "${MOUNTS}" \
...@@ -97,4 +98,4 @@ for ((i=1; i<=${NUM_DECODE_WORKERS}; i++)); do ...@@ -97,4 +98,4 @@ for ((i=1; i<=${NUM_DECODE_WORKERS}; i++)); do
--ntasks-per-node "${NUM_GPUS_PER_NODE}" \ --ntasks-per-node "${NUM_GPUS_PER_NODE}" \
--jobid "${SLURM_JOB_ID}" \ --jobid "${SLURM_JOB_ID}" \
/mnt/examples/basics/multinode/trtllm/start_trtllm_worker.sh & /mnt/examples/basics/multinode/trtllm/start_trtllm_worker.sh &
done done
\ No newline at end of file
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment