Add SGLang Qwen3-8B torch.profiler harness and per-component latency classifier

[chhwang]

Add SGLang Qwen3-8B torch.profiler harness and per-component latency classifier

Q2 of the Qwen3-on-ARK initiative: instrument SGLang's Qwen3-8B forward
with torch.profiler to produce a ranked per-component latency budget for
both prefill and decode phases.

New files under examples/qwen3/:

• bench/profile_sglang.py — HTTP client that drives SGLang's
  /start_profile//stop_profile endpoints for prefill (prompt=2048,
  max_new_tokens=1) and decode (prompt=2048, max_new_tokens=128) phases.
  Configurable schedule (wait=2, warmup=1, active=3), record_shapes,
  with_stack.
• bench/classify_kernels.py — classifies Chrome-trace kernel events into
  seven component buckets (attention, gemm_attention, gemm_mlp, nccl,
  norms_rope, embed_lm_head, other) using name-pattern matching and
  shape-based GEMM disambiguation for Qwen3-8B at TP=8.
• bench/analyze_profile.sh — runs the torch-profiler skill's
  trace_analyzer.py then classify_kernels.py, writing results to an
  analysis/ directory.
• bench/test_profile_sglang.py — 40+ CPU-only unit tests covering kernel
  classification, GEMM shape disambiguation, profiler config construction,
  argument parsing, and budget formatting.
• PROFILE.md — template with per-component tables for prefill and decode;
  numbers filled out-of-band after profiling on 8×A100.
• bench/reproduce_profile.md — step-by-step reproduction instructions.

CI fix: add --no-install-recommends to apt-get install lcov in
.github/workflows/ut.yml to prevent OOM kill (exit 137) from
fontconfig-config dependency tree on the self-hosted CUDA runner.

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 85.70%. Comparing base (c257202) to head (427d7d1).

Additional details and impacted files

@@           Coverage Diff           @@
##             main     #264   +/-   ##
=======================================
  Coverage   85.70%   85.70%           
=======================================
  Files         129      129           
  Lines        6457     6457           
=======================================
  Hits         5534     5534           
  Misses        923      923           

☔ View full report in Codecov by Harness.
📢 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.

[chhwang]

Closing: the SGLang baseline/profiling harness is kept local for evaluation only and will not be merged into this repo. Only the ARK implementation lands here.