perf: specialize hot paths for common sizes

[DaniPopes]

No description provided.

[codspeed-hq]

Merging this PR will degrade performance by 14.14%

⚡ 81 improved benchmarks
❌ 1 regressed benchmark
✅ 304 untouched benchmarks

⚠️ Please fix the performance issues or acknowledge them on CodSpeed.

Performance Changes

	Benchmark	BASE	HEAD	Efficiency
⚡	fmt/binary/4096	5.3 ms	2.3 ms	×2.3
⚡	fmt/hex/192	6.4 ms	3.6 ms	+80.5%
⚡	fmt/hex/512	14.4 ms	8.1 ms	+77.42%
⚡	fmt/hex/384	11.2 ms	6.3 ms	+76.95%
⚡	fmt/hex/4096	4,519.7 µs	584.9 µs	×7.7
⚡	fmt/hex/256	8 ms	4.5 ms	+77.12%
⚡	most_significant_bits/4096/4096	28.9 µs	26.1 µs	+10.88%
⚡	fmt/octal/256	8.6 ms	7.3 ms	+18.66%
⚡	fmt/octal/4096	4.4 ms	1.3 ms	×3.5
⚡	fmt/octal/512	15.8 ms	13.7 ms	+15.13%
⚡	from/f32/128	366 µs	293.9 µs	+24.5%
⚡	from/f64/128	354 µs	301.6 µs	+17.36%
⚡	overflowing_shr/128	357 µs	311.6 µs	+14.57%
⚡	parse/binary/128/zero	559.6 µs	198.3 µs	×2.8
⚡	parse/binary/256/zero	679.8 µs	287.9 µs	×2.4
⚡	parse/binary/192/max	33.5 ms	11.4 ms	×2.9
⚡	parse/binary/192/zero	598.8 µs	248.7 µs	×2.4
⚡	parse/binary/256/max	51.7 ms	15.2 ms	×3.4
⚡	parse/binary/384/zero	875 µs	410.9 µs	×2.1
⚡	parse/binary/4096/max	77.9 ms	2.4 ms	×32
...	...	...	...	...

ℹ️ Only the first 20 benchmarks are displayed. Go to the app to view all benchmarks.

---

_{Comparing DaniPopes:dani/perf-optimizations (75444af) with main (c147f59)}

[DaniPopes]

Split into individual PRs: #560, #561, #562, #563, #564, #565