Revert back to iterating over lines (#680)

## Summary

Partially reverts #663 to iterating over lines, but keeps the skipping
of blank newlines.

## Details

#663 switched the HTTP backend to iterating over byte strings. The
problem is that is did not handle the case where a line was split over
multiple iterations.

## Test Plan

Run a benchmark with known errored request rate (preferably 0) and
ensure that there are no failed requests due to `orjson.JSONDecodeError:
unexpected end of data`.

---

- [x] "I certify that all code in this PR is my own, except as noted
below."

## Use of AI

- [ ] Includes AI-assisted code completion
- [ ] Includes code generated by an AI application
- [ ] Includes AI-generated tests (NOTE: AI written tests should have a
docstring that includes `## WRITTEN BY AI ##`)

Author: sjmonson

src/guidellm/backends/openai/http.py

@@ -473,11 +473,10 @@ async def _aiter_lines(self, stream: httpx.Response) -> AsyncIterator[str]:
         :param stream: HTTP response object with streaming content
         :yield: Lines of text from the response stream
         """
-        async for part in stream.aiter_bytes():
-            for line in part.split(b"\n\n"):
-                if not line:
-                    continue  # Skip blank lines
-                yield line.decode("utf-8").strip()
+        async for line in stream.aiter_lines():
+            if not line.strip():
+                continue  # Skip blank lines
+            yield line
 
     def _build_headers(
         self, existing_headers: dict[str, str] | None = None