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 15, 06:00 UTC
Revert "[Build/CI] Add tracing deps to vllm container image (#15224)" (#19378)
kourosh hakhamaneshi committed
Jun 12, 2025 at 17:26 UTC
e6aab5de2999187c6cf0206f2d63ab6d7a0b6964
2 files changed
+5
-4
.buildkite/test-pipeline.yaml
+5
@@ -177,6 +177,11 @@ steps:
177
- tests/tracing
178
commands:
179
- pytest -v -s metrics
180
+ - "pip install \
181
+ 'opentelemetry-sdk>=1.26.0' \
182
+ 'opentelemetry-api>=1.26.0' \
183
+ 'opentelemetry-exporter-otlp>=1.26.0' \
184
+ 'opentelemetry-semantic-conventions-ai>=0.4.1'"
185
- pytest -v -s tracing
186
187
##### fast check tests #####
requirements/common.txt
-4
@@ -44,7 +44,3 @@ watchfiles # required for http server to monitor the updates of TLS files
44
python-json-logger # Used by logging as per examples/others/logging_configuration.md
45
scipy # Required for phi-4-multimodal-instruct
46
ninja # Required for xgrammar, rocm, tpu, xpu
47
-opentelemetry-sdk>=1.26.0 # vllm.tracing
48
-opentelemetry-api>=1.26.0 # vllm.tracing
49
-opentelemetry-exporter-otlp>=1.26.0 # vllm.tracing
50
-opentelemetry-semantic-conventions-ai>=0.4.1 # vllm.tracing