[None][docs] drop deleted accuracy_eval/gen_server_config from disagg benchmark README

[imitater-dou]

What

In examples/disaggregated/slurm/benchmark/README.md:

• Drop deleted Supporting scripts entries accuracy_eval.sh and gen_server_config.py.
• Note that submit.py invokes lm_eval directly when accuracy evaluation is enabled.
• Align the Accuracy Evaluation YAML sample with config.yaml / submit.py (per-task nested schema).
• Mention run_benchmark_aiperf.sh alongside the other benchmark runners.

Why

• accuracy_eval.sh was removed in [None] [feat] Support multiple accuracy tasks for slurm scripts #10500 (accuracy is inlined via lm_eval in submit.py).
• gen_server_config.py was removed in [None] [feat] Enhancements to slurm scripts #10112.
• The old flat tasks: "gsm8k,..." sample no longer matches the live config schema.

How I checked

Verified on main @ 96a25c4:

• accuracy_eval.sh / gen_server_config.py return 404 under examples/disaggregated/ and examples/disaggregated/slurm/benchmark/.
• Directory listing includes run_benchmark_aiperf.sh, which the README omitted.
• Live config.yaml uses nested accuracy.tasks.<name> with model / model_args_extra / extra_kwargs.
• submit.py writes per-task logs under accuracy_eval_<task> and invokes lm_eval directly.

Dev Engineer Review

• Updated examples/disaggregated/slurm/benchmark/README.md to match the current benchmark workflow.
• Removed references to deleted accuracy_eval.sh and gen_server_config.py scripts.
• Documented direct lm_eval execution through submit.py.
• Updated the accuracy evaluation example to use nested per-task settings and gsm8k.
• Added run_benchmark_aiperf.sh to the benchmark runner documentation.
• No source-code or API changes are included.

QA Engineer Review

No test changes.

Per-File QA Perspective

• examples/disaggregated/slurm/benchmark/README.md: Documentation-only change. Verify that the documented lm_eval command, nested accuracy configuration, per-task result directories, and run_benchmark_aiperf.sh usage match the current scripts and produce the expected benchmark outputs.

[coderabbitai]

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: 69065e78-4947-4440-a1fd-51f74eda463b

📥 Commits

Reviewing files that changed from the base of the PR and between 96a25c4 and 896918e.

📒 Files selected for processing (1)

• examples/disaggregated/slurm/benchmark/README.md

Included review availability: Your plan provides up to 12 included reviews per hour; 7 remain after this review.

---

Walkthrough

The benchmark README now documents run_benchmark_aiperf.sh, direct lm_eval usage through submit.py, per-task accuracy settings, and task-specific result directories.

Changes

Benchmark documentation

Layer / File(s)	Summary
Accuracy evaluation documentation examples/disaggregated/slurm/benchmark/README.md	The README lists the updated benchmark scripts, documents nested per-task accuracy settings with gsm8k, describes task-specific result directories, and preserves the YAML code fence.

Priority: ⬇️ Low

Estimated code review effort: 1 (Trivial) | ~3 minutes

Merge Risk: ⚪ Minimal · up to 89691

Benchmark documentation now reflects the current accuracy-evaluation workflow and runner scripts, with no remaining merge-readiness risk identified.

Suggested reviewers: bowenfu

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title clearly identifies a documentation update that removes references to deleted benchmark scripts. It uses the required ticket and type format and is concise.
Description check	✅ Passed	The description explains what changed, why the changes were needed, and how the author verified the documentation against the current repository state. The testing details are appropriate for a docume…
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check. Docstring coverage is scoped to functions touched by this diff. Analyzed 0 functions across 0…
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests

---

_{Comment @coderabbitai help to get the list of available commands.}