A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 6, 17:00 UTC
[Build] Fix API rate limit exceeded when using `VLLM_USE_PRECOMPILED=1` (#36229)
Signed-off-by: elvischenv <219235043+elvischenv@users.noreply.github.com> Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com> Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
elvischenv committed
Mar 16, 2026 at 20:09 UTC
d61d2b08e99e311976d6622a991de7603034b174
1 file changed
+11
-6
setup.py
+11
-6
@@ -657,13 +657,18 @@ class precompiled_wheel_utils:
657
def get_base_commit_in_main_branch() -> str:
658
try:
659
# Get the latest commit hash of the upstream main branch.
660
- resp_json = subprocess.check_output(
661
- [
662
- "curl",
663
- "-s",
664
- "https://api.github.com/repos/vllm-project/vllm/commits/main",
660
+ curl_cmd = [
661
+ "curl",
662
+ "-s",
663
+ "https://api.github.com/repos/vllm-project/vllm/commits/main",
664
+ ]
665
+ github_token = os.getenv("GH_TOKEN", os.getenv("GITHUB_TOKEN"))
666
+ if github_token:
667
+ curl_cmd += [
668
+ "-H",
669
+ f"Authorization: token {github_token}",
670
]
666
- ).decode("utf-8")
671
+ resp_json = subprocess.check_output(curl_cmd).decode("utf-8")
672
upstream_main_commit = json.loads(resp_json)["sha"]
673
print(f"Upstream main branch latest commit: {upstream_main_commit}")
674