minor performance updates

[tpae]

Summary

While investigating #47 , I noticed minor optimization to be had for Swift Jinja package.

Related PRs:
huggingface/swift-jinja#24
huggingface/swift-transformers#226

Before:

Server	Model	TTFT avg (ms)	Total avg (ms)	Chars/s avg	TTFT rel	Total rel	Chars/s rel	Success
Osaurus	llama-3.2-3b-instruct-4bit	89	1325	553	0%	0%	0%	100%
Ollama	llama3.2	59	1669	439	+33%	-26%	-20%	100%
LM Studio	llama-3.2-3b-instruct	56	1159	618	+37%	+13%	+12%	100%

After:

Server	Model	TTFT avg (ms)	Total avg (ms)	Chars/s avg	TTFT rel	Total rel	Chars/s rel	Success
Osaurus	llama-3.2-3b-instruct-4bit	86	1314	558	0%	0%	0%	100%
Ollama	llama3.2	58	1655	434	+32%	-26%	-22%	100%
LM Studio	llama-3.2-3b-instruct	56	1203	610	+34%	+8%	+9%	100%

Although the benchmark performance seems very minor (maybe 3% closer to LM Studio), Jinja optimization should have lasting effects beyond the benchmarks.

I will be getting back to the drawing board to find some other areas for improvements. ✏️

Changes

• Behavior change
• UI change (screenshots below)
• Refactor / chore
• Tests
• Docs

Checklist

• I have read CONTRIBUTING.md
• I added/updated tests where reasonable
• I updated docs/README as needed
• I verified build on macOS with Xcode 16.4+