Skip to content

Add sidecar GPU/CPU memory+utilization monitor for HF PTQ #2000

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

Open
Fridah-nv wants to merge 4 commits into
base: main
Choose a base branch
from
Open

Add sidecar GPU/CPU memory+utilization monitor for HF PTQ #2000

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
753cfff
Add sidecar GPU/CPU memory+utilization monitor for HF PTQ
Fridah-nv Jul 21, 2026
11d95e6
Address PR #2000 review feedback for mem_monitor sidecar
Fridah-nv Jul 21, 2026
973fd8f
Add GPU power/temperature and CPU total/free to mem_monitor sidecar
Fridah-nv Jul 22, 2026
a77e58a
mem_monitor: accept space-separated --gpus; address review comments
Fridah-nv Jul 23, 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
1 change: 1 addition & 0 deletions examples/hf_ptq/requirements.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,6 @@
compressed-tensors
fire
flash-attn>=2.6.0
psutil
transformers_stream_generator
zstandard
11 changes: 10 additions & 1 deletion examples/hf_ptq/scripts/huggingface_example.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -173,7 +173,16 @@ if [[ $TASKS =~ "quant" ]] || [[ ! -d "$SAVE_PATH" ]] || [[ ! $(ls -A $SAVE_PATH
else
QUANT_SPEC_ARGS="--qformat=${QFORMAT// /,}"
fi
python hf_ptq.py \
# Opt-in memory/utilization sidecar: wraps the run and writes a CSV trace +
# peak summary under SAVE_PATH. Off by default (no behavior change).
MEM_MON_PREFIX=()
if [[ "${MEM_MONITOR:-0}" == "1" ]]; then
MEM_MON_PREFIX=(python scripts/mem_monitor.py \
--gpus "${CUDA_VISIBLE_DEVICES-all}" \
--out "$SAVE_PATH/mem_trace.csv" \
--summary "$SAVE_PATH/mem_peak.txt" --)
fi
"${MEM_MON_PREFIX[@]}" python hf_ptq.py \
--pyt_ckpt_path=$MODEL_PATH \
--export_path=$SAVE_PATH \
--sparsity_fmt=$SPARSITY_FMT \
Expand Down
Loading
Loading