add tracer in v1 to log generator perf metrics

[JenniferWang]

Summary:

tl;dr

Add tracer in v1 to log perf metrics to wandb

V0 vs V1 Metrics Parity Comparison

Category	v0 Metric	v1 Metric	Parity
Generate - Request Count	generator/generate/count_requests (SUM)	generator/generate/count_requests (SUM)	✅ Same
Generate - Completion Count	generator/generate/count_sequences_completed (SUM)	generator/generate/count_sequences_completed (SUM)	✅ Same
Generate - E2E Timing	generator_perf/generate/* (Tracer, GPU)	generator_perf/generate/* (Tracer, GPU)	✅ Same
Update - Pending Requests	generator_perf/update_weights/sum_pending_gen_requests (SUM)	N/A - AsyncLLM handles internally	⚠️ Skip (by design)
Update - Wait for Generation	generator_perf/update_weights/avg_waiting_for_generation_duration_s (MEAN)	generator_perf/update_weights/pause_generation_duration_s (MEAN)	✅ Equivalent - renamed for clarity
Update - Fetch Weights	generator_perf/update_weights/wait_fetch_weights (MEAN)	generator_perf/update_weights/worker_load_weights_duration_s (MEAN)	✅ Equivalent - renamed for clarity
Worker - Update Timing	generator_perf/update_weights/generator_worker_update/* (trace, GPU)	generator_perf/update_weights/generator_worker_update/* (trace, GPU)	✅ Same

Test Plan

Main GRPO app: python -m apps.grpo.main --config apps/grpo/qwen3_1_7b.yaml

wandb: Run `wandb offline` to turn off syncing.
wandb: Syncing run drawn-waterfall-686
wandb: ⭐️ View project at https://meta.wandb.io/jiyue/grpo-training
wandb: 🚀 View run at https://meta.wandb.io/jiyue/grpo-training/runs/6pltx38p
wandb: Detected [openai] in use.
....
rvability.metric_actors.GlobalLoggingActor global_logger>] === [global_reduce] - METRICS STEP 1 ===
  ...
  generator/generate/count_requests: 13.0
  generator/generate/count_sequences_completed: 96.0
  generator_perf/generate/total_duration_avg_s: 3.6518315022786463
  generator_perf/generate/total_duration_max_s: 9.2080615234375
  generator_perf/update_weights/pause_generation_duration_s: 2.8634108749683946
  generator_perf/update_weights/resume_generation_duration_s: 1.918897032737732e-05
  generator_perf/update_weights/worker_load_weights_duration_s: 3.506648204056546
  ...

Make sure integration tests that do not initialize the tracer still works
pytest tests/integration_tests/test_generator_lifecycle.py -v -s

Next Steps

[ ] implement the prefetch logic & shared memory
[-] Add metric similar to generator v0
[ ] Perf/Throughput testing compared to generator v0

Differential Revision: D91038187

[meta-codesync]

@JenniferWang has exported this pull request. If you are a Meta employee, you can view the originating Diff in D91038187.

[allenwang28]

Review automatically exported from Phabricator review in Meta.

[codecov-commenter]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 71.40%. Comparing base (080770c) to head (dc35fed).
⚠️ Report is 14 commits behind head on main.

Additional details and impacted files

@@            Coverage Diff             @@
##             main     #720      +/-   ##
==========================================
- Coverage   78.33%   71.40%   -6.93%     
==========================================
  Files          36       41       +5     
  Lines        4209     4288      +79     
==========================================
- Hits         3297     3062     -235     
- Misses        912     1226     +314     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.