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, 20:15 UTC
[CI] Remove Duplicated Tests (#35199)
Signed-off-by: Robert Shaw <robshaw@redhat.com> Co-authored-by: Robert Shaw <robshaw@redhat.com>
Robert Shaw committed
Feb 24, 2026 at 10:53 UTC
60da0e1544086949e7926623cbb708f20c489268
1 file changed
+1
-11
.buildkite/test_areas/kernels.yaml
+1
-11
@@ -115,6 +115,7 @@ steps:
115
- pytest -v -s tests/kernels/moe/test_nvfp4_moe.py
116
- pytest -v -s tests/kernels/moe/test_ocp_mx_moe.py
117
- pytest -v -s tests/kernels/moe/test_flashinfer.py
118
+ - pytest -v -s kernels/moe/test_flashinfer_moe.py
119
- pytest -v -s tests/kernels/moe/test_cutedsl_moe.py
120
# e2e
121
- pytest -v -s tests/models/quantization/test_nvfp4.py
@@ -156,14 +157,3 @@ steps:
157
- pytest -v -s kernels/moe/test_deepep_moe.py
158
- pytest -v -s kernels/moe/test_pplx_cutlass_moe.py
159
# - pytest -v -s kernels/moe/test_pplx_moe.py - failing on main
159
-
160
-- label: Kernels Fp4 MoE Test (B200)
161
- timeout_in_minutes: 60
162
- device: b200
163
- num_devices: 1
164
- optional: true
165
- commands:
166
- - pytest -v -s kernels/moe/test_cutedsl_moe.py
167
- - pytest -v -s kernels/moe/test_flashinfer_moe.py
168
- - pytest -v -s kernels/moe/test_nvfp4_moe.py
169
- - pytest -v -s kernels/moe/test_ocp_mx_moe.py