lazy_frame join_asof and then sink_parquet not supported

[guanqun]

Checks

• I have checked that this issue has not already been reported.
• I have confirmed this bug exists on the latest version of Polars.

Reproducible example

import polars as pl

a_df = pl.LazyFrame({"a": [1, 2, 3]})
b_df = pl.LazyFrame({"a": [2, 5, 6], "b": [1, 2, 3]})

a_df.join_asof(b_df, on='a', strategy='backward').sink_parquet("out.parquet")

Log output

2440 else:
   2441     # Handle empty dict input
   2442     storage_options = None
-> 2444 return lf.sink_parquet(
   2445     path=normalize_filepath(path),
   2446     compression=compression,
   2447     compression_level=compression_level,
   2448     statistics=statistics,
   2449     row_group_size=row_group_size,
   2450     data_page_size=data_page_size,
   2451     maintain_order=maintain_order,
   2452     cloud_options=storage_options,
   2453     credential_provider=credential_provider,
   2454     retries=retries,
   2455 )

InvalidOperationError: sink_Parquet(ParquetWriteOptions { compression: Zstd(None), statistics: StatisticsOptions { min_value: true, max_value: true, distinct_count: false, null_count: true }, row_group_size: None, data_page_size: None, maintain_order: true }) not yet supported in standard engine. Use 'collect().write_Parquet(ParquetWriteOptions { compression: Zstd(None), statistics: StatisticsOptions { min_value: true, max_value: true, distinct_count: false, null_count: true }, row_group_size: None, data_page_size: None, maintain_order: true })()'

### Issue description

it seems that this operation is not supported.

### Expected behavior

we should at least allow this case with `join_asof()`, since it assume the key is sorted, and we can incrementally process it and then write the output to disk.

### Installed versions

<details>

--------Version info---------
Polars: 1.19.0
Index type: UInt32
Platform: Linux-5.15.0-82-generic-x86_64-with-glibc2.35
Python: 3.12.6 | packaged by conda-forge | (main, Sep 22 2024, 14:16:49) [GCC 13.3.0]
LTS CPU: False

----Optional dependencies----
adbc_driver_manager
altair 5.4.0
azure.identity
boto3
cloudpickle 3.1.0
connectorx
deltalake
fastexcel
fsspec
gevent
google.auth
great_tables
matplotlib 3.9.2
nest_asyncio 1.6.0
numpy 2.2.0
openpyxl
pandas 2.2.3
pyarrow 17.0.0
pydantic
pyiceberg
sqlalchemy
torch
xlsx2csv
xlsxwriter

</details>

[guanqun]

feel free to move this ticket as a feature request.

if someone is willing to give some high level guidelines on how we should support this, I'm happy to dive into it and make it work.