Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
5 changes: 3 additions & 2 deletions examples/disaggregated/slurm/benchmark/disaggr_torch.slurm
Original file line number Diff line number Diff line change
Expand Up @@ -83,8 +83,6 @@ echo "ntasks_per_node: ${ntasks_per_node}"
echo "==========================================="


nsys_on=""
# nsys_on=${full_logdir} # Uncomment this line to enable Nsys profiling
numa_bind=true # Only allocate memory from nodes, this only works on GB200
ctx_max_seq_len=$((isl + 10))
gen_max_seq_len=$((isl + osl + 10))
Expand All @@ -96,6 +94,9 @@ logdir=${workdir}/slurm-${SLURM_JOB_ID}/benchmark-${isl}-${osl}
mkdir -p ${logdir}
full_logdir=${logdir}/ctx${num_ctx_servers}_gen${num_gen_servers}_dep${gen_tp_size}_batch${gen_batch_size}_eplb${eplb_num_slots}_mtp${mtp_size}

nsys_on=""
# nsys_on=${full_logdir} # Uncomment this line to enable Nsys profiling

echo "concurrency: ${concurrency}"

ctx_gpus=$((num_ctx_servers * ctx_tp_size * ctx_pp_size))
Expand Down
4 changes: 2 additions & 2 deletions examples/disaggregated/slurm/benchmark/start_worker.sh
Original file line number Diff line number Diff line change
Expand Up @@ -65,14 +65,14 @@ else
nsys_file=${nsys_folder}/nsys_worker_proc_${instance_id}_${SLURM_PROCID}
export TLLM_PROFILE_RECORD_GC=1
export TLLM_NVTX_DEBUG=1
if [ "${role}" = "GEN" ]; then
if [ "${role}" = "GEN" ] && [ "$SLURM_PROCID" = "0" ]; then
export TLLM_PROFILE_START_STOP=200-250
nsys_prefix="nsys profile -e \"NSYS_MPI_STORE_TEAMS_PER_RANK=1\" -o ${nsys_file} -f true -t cuda,nvtx,python-gil -c cudaProfilerApi --cuda-graph-trace node --capture-range-end=stop --gpu-metrics-devices=none"
echo "nsys_prefix: ${nsys_prefix}"
elif [ "${role}" = "CTX" ]; then
echo "nsys is not enabled on ctx_gpus"
fi
trtllm-llmapi-launch ${numa_bind_cmd} ${nsys_prefix} \
${nsys_prefix} trtllm-llmapi-launch ${numa_bind_cmd} \
trtllm-serve ${model_path} \
--host $(hostname) --port ${port} \
--extra_llm_api_options ${config_file}
Expand Down