install: remove nvidia-nvshmem-cu12 from package dependency (#1426)

## 📌 Description

The dependency is not required because:

* For x86_64 user environments that installs pytorch from pypi,
nvidia-nvshmem-cu12 is already a torch dependency

(https://github.com/pytorch/pytorch/blob/3f1636ebef9b45e8a3cb0eb20d327ee6acb74be0/.github/scripts/generate_binary_build_matrix.py#L44-L95),
and flashinfer depends on torch, there is no need to specify another
nvidia-nvshmem-cu12 dependency in flashinfer.
* For user environments where nvidia-nvshmem-cu12 is not a torch
dependency (like in nvidia's pytorch container),
  nvshmem is installed at system wide.

## 🔍 Related Issues

Fixes #1387

## 🚀 Pull Request Checklist

Thank you for contributing to FlashInfer! Before we review your pull
request, please make sure the following items are complete.

### ✅ Pre-commit Checks

- [X] I have installed `pre-commit` by running `pip install pre-commit`
(or used your preferred method).
- [X] I have installed the hooks with `pre-commit install`.
- [X] I have run the hooks manually with `pre-commit run --all-files`
and fixed any reported issues.

> If you are unsure about how to set up `pre-commit`, see [the
pre-commit documentation](https://pre-commit.com/).

## 🧪 Tests

- [X] Tests have been added or updated as needed.
- [X] All tests are passing (`unittest`, etc.).

Signed-off-by: Emilien Macchi <[email protected]>

Author: EmilienM

setup.py

@@ -61,7 +61,6 @@ def generate_build_meta(aot_build_meta: dict) -> None:
     "cuda-python",
     "pynvml",
     "einops",
-    "nvidia-nvshmem-cu12",
     "nvidia-cudnn-frontend>=1.13.0",
 ]
 generate_build_meta({})