fix(cleanup): ensure repository URL has no trailing slash (#1759)

<!-- .github/pull_request_template.md -->

## 📌 Description
Remove trailing slash from FLASHINFER_CUBINS_REPOSITORY before
concatenating the filename, to avoid redundant double slashes in the
URL. Even though servers may handle double slashes, this makes URL
construction consistent and cleaner.
<!-- What does this PR do? Briefly describe the changes and why they’re
needed. -->

## 🔍 Related Issues

<!-- Link any related issues here -->

## 🚀 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

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

## Reviewer Notes

<!-- Optional: anything you'd like reviewers to focus on, concerns, etc.
-->

---------

Signed-off-by: Tarun Kumar <[email protected]>

Author: tarukumar

flashinfer/artifacts.py

@@ -18,7 +18,7 @@
 import re
 import time
 from concurrent.futures import ThreadPoolExecutor, as_completed
-
+from urllib.parse import urljoin
 import requests  # type: ignore[import-untyped]
 import shutil
 
@@ -94,6 +94,7 @@ class MetaInfoHash:
 
 
 def get_cubin_file_list():
+    base = FLASHINFER_CUBINS_REPOSITORY.rstrip("/")
     cubin_files = [
         (ArtifactPath.TRTLLM_GEN_FMHA + "include/flashInferMetaInfo", ".h"),
         (ArtifactPath.TRTLLM_GEN_GEMM + "include/flashinferMetaInfo", ".h"),
@@ -108,7 +109,7 @@ def get_cubin_file_list():
         cubin_files += [
             (kernel + name, extension)
             for name, extension in get_available_cubin_files(
-                FLASHINFER_CUBINS_REPOSITORY + "/" + kernel
+                urljoin(base + "/", kernel)
             )
         ]
     return cubin_files

flashinfer/jit/cubin_loader.py

@@ -17,6 +17,7 @@
 import ctypes
 import hashlib
 import os
+from urllib.parse import urljoin
 import shutil
 import time
 
@@ -154,7 +155,9 @@ def get_cubin(name, sha256, file_extension=".cubin", session=None):
     if cubin:
         return cubin
     # either the file does not exist or it is corrupted, we'll download a new one.
-    uri = FLASHINFER_CUBINS_REPOSITORY + "/" + cubin_fname
+
+    base = FLASHINFER_CUBINS_REPOSITORY.rstrip("/")
+    uri = urljoin(base + "/", cubin_fname)
     logger.info(f"Fetching cubin {name} from {uri}")
     download_file(uri, cubin_path, session=session)
     return load_cubin(cubin_path, sha256)