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, 20:45 UTC
[ci] Mark tensorizer as soft fail and separate from grouped test (#6810)
[ci] Mark tensorizer test as soft fail and separate it from grouped test in fast check (#6810) Signed-off-by: kevin <kevin@anyscale.com>
Kevin H. Luu committed
Jul 25, 2024 at 18:08 UTC
2eb9f4ff262bb39859baebf8d2109abcdadee860
1 file changed
+3
-2
.buildkite/test-pipeline.yaml
+3
-2
@@ -17,11 +17,10 @@ steps:
17
- pytest -v -s test_utils.py # Utils
18
- pytest -v -s worker # Worker
19
20
-- label: Tensorizer, Metrics, Tracing Test
20
+- label: Metrics, Tracing Test
21
fast_check: true
22
fast_check_only: true
23
commands:
24
- - apt-get install -y curl libsodium23 && pytest -v -s tensorizer_loader # Tensorizer
24
- pytest -v -s metrics # Metrics
25
- "pip install \
26
opentelemetry-sdk \
@@ -221,6 +220,8 @@ steps:
220
221
- label: Tensorizer Test
222
#mirror_hardwares: [amd]
223
+ soft_fail: true
224
+ fast_check: true
225
commands:
226
- apt-get install -y curl libsodium23
227
- export VLLM_WORKER_MULTIPROC_METHOD=spawn