[Bugfix][CI] Normalize NIXL connector CUDA wheel installs (#44266)

Signed-off-by: Alec Flowers <aflowers@nvidia.com>
This commit is contained in:
Alec
2026-06-01 19:34:05 -07:00
committed by GitHub
parent 2588ec4f0a
commit 816cc73a9b
3 changed files with 49 additions and 10 deletions
+39
View File
@@ -0,0 +1,39 @@
#!/bin/bash
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
set -euo pipefail
REQUIREMENTS_FILE="${KV_CONNECTORS_REQUIREMENTS:-/vllm-workspace/requirements/kv_connectors.txt}"
uv pip install --system -r "${REQUIREMENTS_FILE}"
NIXL_METADATA=$(python3 - <<'PY'
import importlib.metadata as metadata
import torch
cuda_version = torch.version.cuda
if cuda_version is None:
raise SystemExit("torch.version.cuda is not set")
print(cuda_version.split(".", 1)[0], metadata.version("nixl"))
PY
)
read -r CUDA_MAJOR NIXL_VERSION <<<"${NIXL_METADATA}"
# nixl>=1.1.0 can install multiple CUDA wheel variants. Keep only the variant
# matching this CI image so nixl_ep_cpp links against the available libcudart.
uv pip uninstall --system nixl-cu12 nixl-cu13 2>/dev/null || true
uv pip install --system --no-deps "nixl-cu${CUDA_MAJOR}==${NIXL_VERSION}"
python3 - <<'PY'
import importlib.metadata as metadata
for package_name in ("nixl", "nixl-cu12", "nixl-cu13"):
try:
version = metadata.version(package_name)
except metadata.PackageNotFoundError:
version = "not installed"
print(f"{package_name}: {version}")
PY
+9 -9
View File
@@ -11,7 +11,7 @@ steps:
- vllm/distributed/kv_transfer/kv_connector/v1/nixl/
- tests/v1/kv_connector/nixl_integration/
commands:
- uv pip install --system -r /vllm-workspace/requirements/kv_connectors.txt
- bash /vllm-workspace/.buildkite/scripts/install-kv-connectors.sh
- bash v1/kv_connector/nixl_integration/config_sweep_accuracy_test.sh
- label: Distributed FlashInfer NixlConnector PD accuracy (4 GPUs)
key: distributed-flashinfer-nixlconnector-pd-accuracy-4-gpus
@@ -22,7 +22,7 @@ steps:
- vllm/distributed/kv_transfer/kv_connector/v1/nixl/
- tests/v1/kv_connector/nixl_integration/
commands:
- uv pip install --system -r /vllm-workspace/requirements/kv_connectors.txt
- bash /vllm-workspace/.buildkite/scripts/install-kv-connectors.sh
- FLASHINFER=1 bash v1/kv_connector/nixl_integration/config_sweep_accuracy_test.sh
- label: DP EP Distributed NixlConnector PD accuracy tests (4 GPUs)
@@ -34,7 +34,7 @@ steps:
- vllm/distributed/kv_transfer/kv_connector/v1/nixl/
- tests/v1/kv_connector/nixl_integration/
commands:
- uv pip install --system -r /vllm-workspace/requirements/kv_connectors.txt
- bash /vllm-workspace/.buildkite/scripts/install-kv-connectors.sh
- DP_EP=1 bash v1/kv_connector/nixl_integration/config_sweep_accuracy_test.sh
- label: CrossLayer KV layout Distributed NixlConnector PD accuracy tests (4 GPUs)
@@ -46,7 +46,7 @@ steps:
- vllm/distributed/kv_transfer/kv_connector/v1/nixl/
- tests/v1/kv_connector/nixl_integration/
commands:
- uv pip install --system -r /vllm-workspace/requirements/kv_connectors.txt
- bash /vllm-workspace/.buildkite/scripts/install-kv-connectors.sh
- CROSS_LAYERS_BLOCKS=True bash v1/kv_connector/nixl_integration/config_sweep_accuracy_test.sh
- label: Hybrid SSM NixlConnector PD accuracy tests (4 GPUs)
@@ -58,7 +58,7 @@ steps:
- vllm/distributed/kv_transfer/kv_connector/v1/nixl/
- tests/v1/kv_connector/nixl_integration/
commands:
- uv pip install --system -r /vllm-workspace/requirements/kv_connectors.txt
- bash /vllm-workspace/.buildkite/scripts/install-kv-connectors.sh
- HYBRID_SSM=1 bash v1/kv_connector/nixl_integration/config_sweep_accuracy_test.sh
- label: MultiConnector (Nixl+Offloading) PD accuracy (2 GPUs)
@@ -73,7 +73,7 @@ steps:
- vllm/distributed/kv_transfer/kv_connector/v1/offloading/
- tests/v1/kv_connector/nixl_integration/
commands:
- uv pip install --system -r /vllm-workspace/requirements/kv_connectors.txt
- bash /vllm-workspace/.buildkite/scripts/install-kv-connectors.sh
- bash v1/kv_connector/nixl_integration/run_multi_connector_accuracy_test.sh
- label: NixlConnector PD + Spec Decode acceptance (2 GPUs)
@@ -87,7 +87,7 @@ steps:
- vllm/v1/worker/kv_connector_model_runner_mixin.py
- tests/v1/kv_connector/nixl_integration/
commands:
- uv pip install --system -r /vllm-workspace/requirements/kv_connectors.txt
- bash /vllm-workspace/.buildkite/scripts/install-kv-connectors.sh
- bash v1/kv_connector/nixl_integration/config_sweep_spec_decode_test.sh
- label: MultiConnector (Nixl+Offloading) PD edge cases (2 GPUs)
@@ -102,5 +102,5 @@ steps:
- vllm/distributed/kv_transfer/kv_connector/v1/offloading/
- tests/v1/kv_connector/nixl_integration/
commands:
- uv pip install --system -r /vllm-workspace/requirements/kv_connectors.txt
- bash v1/kv_connector/nixl_integration/run_multi_connector_edge_case_test.sh
- bash /vllm-workspace/.buildkite/scripts/install-kv-connectors.sh
- bash v1/kv_connector/nixl_integration/run_multi_connector_edge_case_test.sh
+1 -1
View File
@@ -86,7 +86,7 @@ steps:
- tests/v1/metrics
- tests/entrypoints/openai/correctness/test_lmeval.py
commands:
- uv pip install --system -r /vllm-workspace/requirements/kv_connectors.txt
- bash /vllm-workspace/.buildkite/scripts/install-kv-connectors.sh
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
# split the test to avoid interference
- pytest -v -s -m 'not cpu_test' v1/core