release: bump version to v0.2.3 (#932)

This pull request includes a version update in the `version.txt` file to
reflect the new version number.

*
[`version.txt`](diffhunk://#diff-97a08f11d52bb61c11fc6e159245145df32347dd439b9c6e6d94a863f3b1df4bL1-R1):
Updated version number from `0.2.2.post1` to `0.2.3`.

upd

bump version

fix compile (#866)

refactor: change to TORCH_LIBRARY (#823)

This PR updates FlashInfer's C++/CUDA extensions from pybind11 modules
to `torch.libraries`, which is recommended since PyTorch 2.5.

This is mainly implemented in #764. We have investigated that the issue
in #820 was not caused by this PR, so we're opening it up again.

---------

Signed-off-by: youkaichao <[email protected]>
Signed-off-by: abmfy <[email protected]>
Co-authored-by: youkaichao <[email protected]>
Co-authored-by: Zihao Ye <[email protected]>

set pip path (#834)

verified

Version bump: v0.2.0.post2 (#768)

Release a version before v0.2.1 (which includes a bunch of mla updates).

upd

ci: Pass FLASHINFER_ENABLE_SM90 to setup.py (#685)

feat: add gelu_and_mul (#474)

for gemma