rebase: target the official vLLM 0.31.0 release
Use upstream release images at db9527a46873, preserve custom processor conditioning, and include weekly jobs in full Buildkite release validation. Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
This commit is contained in:
1 parent
008fa25263
commit
ed876de879
15 files changed
+142
-45
No files matched your search
@@ -12,24 +12,24 @@ from pathlib import Path
|
||||
def main() -> None:
|
||||
dockerfile = Path(__file__).resolve().parents[3] / "docker" / "Dockerfile.ci"
|
||||
match = re.search(
|
||||
r"^ARG VLLM_PRECOMPILED_WHEEL_COMMIT=([0-9a-f]{40})$",
|
||||
r"^ARG VLLM_VERSION=([0-9]+\.[0-9]+\.[0-9]+)$",
|
||||
dockerfile.read_text(),
|
||||
re.MULTILINE,
|
||||
)
|
||||
if match is None:
|
||||
raise RuntimeError(f"Missing vLLM commit pin in {dockerfile}")
|
||||
expected_commit = match.group(1)
|
||||
raise RuntimeError(f"Missing vLLM release version in {dockerfile}")
|
||||
expected_version = match.group(1)
|
||||
|
||||
import torch
|
||||
import vllm
|
||||
|
||||
assert expected_commit[:8] in vllm.__version__, vllm.__version__
|
||||
assert vllm.__version__ == expected_version, vllm.__version__
|
||||
assert torch.cuda.is_available(), "vLLM runtime check requires a GPU worker"
|
||||
for module in ("flashinfer", "vllm._C_stable_libtorch"):
|
||||
importlib.import_module(module)
|
||||
print(
|
||||
f"Verified vLLM CUDA runtime: vllm={vllm.__version__} "
|
||||
f"commit={expected_commit} torch={torch.__version__} "
|
||||
f"expected={expected_version} torch={torch.__version__} "
|
||||
f"cuda={torch.version.cuda} device={torch.cuda.get_device_name()}"
|
||||
)
|
||||
|
||||
|
||||
Reference in new issue
Block a user