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 7, 17:45 UTC
[ROCm][CI] Amending deletion of AMD mirror (#35322)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Andreas Karatzas committed
Feb 25, 2026 at 16:17 UTC
ed42507f6d6e326663997da5cca6991da5d8a23f
1 file changed
+5
.buildkite/test_areas/entrypoints.yaml
+5
@@ -24,6 +24,11 @@ steps:
24
- pytest -v -s entrypoints/llm --ignore=entrypoints/llm/test_generate.py --ignore=entrypoints/llm/test_collective_rpc.py
25
- pytest -v -s entrypoints/llm/test_generate.py # it needs a clean process
26
- pytest -v -s entrypoints/offline_mode # Needs to avoid interference with other tests
27
+ mirror:
28
+ amd:
29
+ device: mi325_1
30
+ depends_on:
31
+ - image-build-amd
32
33
- label: Entrypoints Integration (API Server 1)
34
timeout_in_minutes: 130