feat: wandb logging for microbenchmarks and lm-eval accuracy - #183
Open
Anirudhaagrawal wants to merge 1 commit into
Open
feat: wandb logging for microbenchmarks and lm-eval accuracy#183Anirudhaagrawal wants to merge 1 commit into
Anirudhaagrawal wants to merge 1 commit into
Conversation
Add Weights & Biases integration to all three microbenchmarks (prefill, decode, stress) and the lm-eval accuracy evaluator, bringing them to parity with the full benchmark system's wandb support. Changes: - Add `wandb: WandbConfig` to `BaseMicrobenchmarkConfig` so all microbench CLIs expose `--wandb.enabled`, `--wandb.project`, etc. - Add `num_gpus` to `StressMicrobenchmarkConfig` for per-GPU throughput metrics (TPS/GPU vs TPS/User plots, the Sarvam/InferenceX style). - Add three lifecycle functions in `wandb_integration.py`: `maybe_init_microbench_wandb_run`, `maybe_log_microbench_results`, `maybe_finish_microbench_wandb_run` with type-specific logging (tables, scalars, plots, artifacts) for prefill/decode/stress. - Wire wandb lifecycle into `runner.run()` (prefill, decode, stress manual/range) and `_run_auto_main()` (stress auto mode). - Add `output_tps_per_gpu` / `input_tps_per_gpu` to StressPointResult, two new stress plots (TPS/GPU vs Load, TPS/GPU vs TPS/User), and TPS/GPU columns in the results table and JSON output. - Add TPS/GPU comparison plots to `veeksha diff` for stress results. - Add `_log_wandb_metrics()` to `LMEvalAccuracyEvaluator.save()` to log per-task accuracy scalars and results table when a wandb run is active. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
ℹ️ Recent review info⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Free Run ID: 📒 Files selected for processing (6)
📝 WalkthroughWalkthroughThis PR integrates Weights & Biases (W&B) logging throughout the evaluator and microbenchmark systems, adds per-GPU throughput metrics to stress benchmarks, and introduces new comparative performance plots. It adds comprehensive W&B helper functions for run initialization, metrics logging, and finalization. Changes
Sequence DiagramsequenceDiagram
participant Runner as Microbench Runner
participant WandB as W&B System
participant Benchmark as Benchmark Executor
participant Results as Results Logger
Runner->>WandB: maybe_init_microbench_wandb_run()
activate WandB
WandB->>WandB: Initialize run with config & tags
deactivate WandB
Runner->>Benchmark: Execute benchmark
activate Benchmark
Benchmark->>Benchmark: Run microbench (prefill/decode/stress)
Benchmark->>Benchmark: Generate results JSON
deactivate Benchmark
Runner->>Results: Print results table
activate Results
Results-->>Runner: Results displayed
deactivate Results
Runner->>WandB: maybe_log_microbench_results()
activate WandB
WandB->>WandB: Log metrics & tables by type
WandB->>WandB: Upload artifacts (JSON/CSV/PNG)
deactivate WandB
Runner->>WandB: maybe_finish_microbench_wandb_run()
activate WandB
WandB->>WandB: Persist run metadata & finalize
deactivate WandB
Estimated code review effort🎯 4 (Complex) | ⏱️ ~60 minutes Poem
Note 🎁 Summarized by CodeRabbit FreeYour organization is on the Free plan. CodeRabbit will generate a high-level summary and a walkthrough for each pull request. For a comprehensive line-by-line review, please upgrade your subscription to CodeRabbit Pro by visiting https://app.coderabbit.ai/login. Comment |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
wandb: WandbConfigtoBaseMicrobenchmarkConfigso all microbench CLIs expose--wandb.*flags (prefill, decode, stress)num_gpustoStressMicrobenchmarkConfigfor TPS/GPU metrics and plots (TPS/GPU vs Load, TPS/GPU vs TPS/User — the Sarvam/InferenceX-style throughput curves)wandb_integration.py:maybe_init_microbench_wandb_run,maybe_log_microbench_results,maybe_finish_microbench_wandb_runwith type-specific logging (tables, scalars, plots, artifacts)runner.run()(all manual/range microbench modes) and_run_auto_main()(stress auto mode)output_tps_per_gpu/input_tps_per_gputoStressPointResult, TPS/GPU columns in rich table and JSON outputveeksha difffor stress results_log_wandb_metrics()toLMEvalAccuracyEvaluator.save()to log per-task accuracy scalars and results table when a wandb run is activeTest plan
make lintpasses (excluding pre-existing black bug inslo/metrics.py)python -m pytest tests/unit/ -x -qpasses (213/214 pass; 1 failure is pre-existing env issue: port 8000 in use)uvx --python 3.14t veeksha stress --helpshows--wandb.*and--num_gpusflagsuvx --python 3.14t veeksha prefill --helpshows--wandb.*flagsuvx --python 3.14t veeksha decode --helpshows--wandb.*flags🤖 Generated with Claude Code
Summary by CodeRabbit