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, 13:30 UTC
[CI/CD][V1] Add spec decode tests to CI (#16900)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Woosuk Kwon committed
Apr 20, 2025 at 22:37 UTC
4c41278b77a8b14fbab6dfeb95d5185c12018fbc
1 file changed
+1
.buildkite/test-pipeline.yaml
+1
@@ -205,6 +205,7 @@ steps:
205
- pytest -v -s v1/sample
206
- pytest -v -s v1/worker
207
- pytest -v -s v1/structured_output
208
+ - pytest -v -s v1/spec_decode
209
- pytest -v -s v1/test_stats.py
210
- pytest -v -s v1/test_utils.py
211
- pytest -v -s v1/test_oracle.py