@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / f9d25c2519
Fork 0

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 16, 22:00 UTC

[Build/CI] Checking/Waiting for the GPU's clean state (#6379)

Alexei-V-Ivanov-AMD committed Jul 12, 2024 at 11:42 UTC f9d25c251907bc8be9b9c712adaf8d3ce631226e
1 file changed +9
.buildkite/run-amd-test.sh
+9
@@ -2,6 +2,15 @@
2 set -ex
3
4 # Print ROCm version
5 +echo "--- Confirming Clean Initial State"
6 +while true; do
7 + sleep 3
8 + if grep -q clean /opt/amdgpu/etc/gpu_state; then
9 + echo "GPUs state is \"clean\""
10 + break
11 + fi
12 +done
13 +
14 echo "--- ROCm info"
15 rocminfo
16