feat: add benchmarking

[besaleli]

Adds:

• Workflow CI for microbenchmarks
• Benchmarks for L2 normalization and postprocessing functions

[codecov-commenter]

Codecov Report

✅ All modified and coverable lines are covered by tests.

Files with missing lines	Coverage Δ
encoderfile/src/inference/embedding.rs	95.83% <100.00%> (+8.87%)	⬆️
...coderfile/src/inference/sequence_classification.rs	100.00% <100.00%> (+11.11%)	⬆️
encoderfile/src/inference/token_classification.rs	97.05% <100.00%> (+19.55%)	⬆️
encoderfile/tests/model_utils.rs	100.00% <100.00%> (ø)

🚀 New features to boost your workflow:

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

[codspeed-hq]

CodSpeed Performance Report

Congrats! CodSpeed is installed 🎉

🆕 11 new benchmarks were detected.

You will start to see performance impacts in the reports once the benchmarks are run from your default branch.

Detected benchmarks

• bench_l2_normalize[Axis(0)]: 1.6 ms
• bench_l2_normalize[Axis(1)]: 3 ms
• embedding_postprocess[(16, 128, 768)]: 25.2 ms
• embedding_postprocess[(64, 512, 1024)]: 311.6 ms
• embedding_postprocess[(8, 16, 384)]: 4.6 ms
• sequence_classification_postprocess[16]: 39.3 µs
• sequence_classification_postprocess[64]: 57.8 µs
• sequence_classification_postprocess[8]: 14.6 µs
• token_classification_postprocess[(16, 128)]: 10.2 ms
• token_classification_postprocess[(64, 512)]: 93.2 ms
• token_classification_postprocess[(8, 16)]: 3.7 ms