dynamo/benchmarks/profiler/utils
MatejKosec 67329d1023
fix: profiler deployment timeout handling for MoE models (#6086)
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
2026-02-09 15:57:59 -08:00
..
config_modifiers fix: profiler deployment timeout handling for MoE models (#6086) 2026-02-09 15:57:59 -08:00
__init__.py chore: update all copyright headers in repo to 2026 (#5130) 2026-01-02 22:08:23 +00:00
aiperf.py chore: update all copyright headers in repo to 2026 (#5130) 2026-01-02 22:08:23 +00:00
config.py feat: SLA Planner configuration support for DEP and TEP VLLM (#4783) 2026-01-14 13:13:44 -08:00
defaults.py feat: remove default model name in Profiler; validate for one of served model name and model path in Profiler (#5950) 2026-02-04 16:21:31 -08:00
dgd_generation.py feat: normalize dynamo namespace computation (#5231) 2026-01-12 19:09:43 +00:00
estimate_perf.py chore: update all copyright headers in repo to 2026 (#5130) 2026-01-02 22:08:23 +00:00
model_info.py chore: update all copyright headers in repo to 2026 (#5130) 2026-01-02 22:08:23 +00:00
pareto.py chore: update all copyright headers in repo to 2026 (#5130) 2026-01-02 22:08:23 +00:00
planner_utils.py chore: update all copyright headers in repo to 2026 (#5130) 2026-01-02 22:08:23 +00:00
plot.py feat: SLA Planner configuration support for DEP and TEP VLLM (#4783) 2026-01-14 13:13:44 -08:00
profile_decode.py chore: update all copyright headers in repo to 2026 (#5130) 2026-01-02 22:08:23 +00:00
profile_prefill.py chore: update all copyright headers in repo to 2026 (#5130) 2026-01-02 22:08:23 +00:00
profiler_argparse.py feat: SLA Planner configuration support for DEP and TEP VLLM (#4783) 2026-01-14 13:13:44 -08:00
profiler_status.py fix: Add status file to prevent output-copier hang on failures (#5898) 2026-02-03 17:25:08 -08:00
search_space_autogen.py fix: check --served-model-name first before --model/--model-path (#5881) 2026-02-02 16:29:42 -08:00