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 11, 20:00 UTC
[ROCm][CI] Skip NVIDIA-Only Prime-RL Test in AMD CI (#29420)
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
Micah Williamson committed
Dec 8, 2025 at 20:14 UTC
78c75033642b8c2832fcfb8d483871b65673326b
1 file changed
+5
.buildkite/scripts/run-prime-rl-test.sh
+5
@@ -12,6 +12,11 @@ REPO_ROOT="$(cd "${SCRIPT_DIR}/../.." && pwd)"
12
PRIME_RL_REPO="https://github.com/PrimeIntellect-ai/prime-rl.git"
13
PRIME_RL_DIR="${REPO_ROOT}/prime-rl"
14
15
+if command -v rocm-smi &> /dev/null || command -v rocminfo &> /dev/null; then
16
+ echo "AMD GPU detected. Prime-RL currently only supports NVIDIA. Skipping..."
17
+ exit 0
18
+fi
19
+
20
echo "Setting up Prime-RL integration test environment..."
21
22
# Clean up any existing Prime-RL directory