GitLab

Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>

Signed-off-by: Neal Vaidya <nealv@nvidia.com>

Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>

Signed-off-by: Guan Luo <41310872+GuanLuo@users.noreply.github.com>

Signed-off-by: Yuewei Na <nv-yna@users.noreply.github.com>
Co-authored-by: Yuewei Na <nv-yna@users.noreply.github.com>

Signed-off-by: Graham King <grahamk@nvidia.com>

Signed-off-by: Alexandre Milesi <milesial@users.noreply.github.com>

Signed-off-by: Jont828 <jt572@cornell.edu>

Signed-off-by: Graham King <grahamk@nvidia.com>

Signed-off-by: Devi Vasudevan <deviv@microsoft.com>
Signed-off-by: devivasudevan <49675305+devivasudevan@users.noreply.github.com>
Co-authored-by: Sertaç Özercan <852750+sozercan@users.noreply.github.com>

Signed-off-by: Graham King <grahamk@nvidia.com>

Signed-off-by: Yuewei Na <nv-yna@users.noreply.github.com>
Signed-off-by: Yuewei Na <248773860+nv-yna@users.noreply.github.com>
Co-authored-by: Yuewei Na <nv-yna@users.noreply.github.com>
Co-authored-by: Tanmay Verma <tanmayv@nvidia.com>

Signed-off-by: mohammedabdulwahhab <furkhan324@berkeley.edu>

Replace PIPE-based stdout/stderr capture with direct file output in LoadGenerator.generate_load() to prevent orphaned aiperf child processes from blocking communicate() indefinitely
Add start_new_session=True so os.killpg() can kill the entire process tree on timeout (not just the main process)
Add unit test validating process-group kill on timeout
Fixes DYN-2086

Signed-off-by: Hannah Zhang <hannahz@nvidia.com>

Signed-off-by: Anant Sharma <anants@nvidia.com>

Signed-off-by: Graham King <grahamk@nvidia.com>

Signed-off-by: Dillon Cullinan <dcullinan@nvidia.com>

Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>

Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>

Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>

Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>

Signed-off-by: Orange Ng <ngquanhao@outlook.com>
Co-authored-by: Neal Vaidya <nealv@nvidia.com>

Wrap wait_for_deployment_ready() in try/except TimeoutError for both prefill and decode profiling sweeps
On timeout: log error, record via add_profiling_error(), clean up the timed-out deployment, and continue to the next parallelization mapping
Previously, a single deployment timeout would crash the entire profiler job

Signed-off-by: ayushag <ayushag@nvidia.com>

Signed-off-by: Dan Gil <dagil@nvidia.com>
Signed-off-by: dagil-nvidia <dagil@nvidia.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Jonathan Tong <jt572@cornell.edu>

Signed-off-by: Dan Gil <dagil@nvidia.com>
Co-authored-by: Cursor <cursoragent@cursor.com>

Signed-off-by: Dan Gil <dagil@nvidia.com>
Co-authored-by: Cursor <cursoragent@cursor.com>

Signed-off-by: Dan Gil <dagil@nvidia.com>
Co-authored-by: Cursor <cursoragent@cursor.com>