@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 2eb9f4ff26
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, 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