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 14, 05:30 UTC
[ci] Rename `test_mxfp4_moe.py` to `test_ocp_mx_moe.py` (#26364)
Signed-off-by: Felix Marty <Felix.Marty@amd.com>
fxmarty-amd committed
Oct 7, 2025 at 18:52 UTC
a38c1bfe09f487cb61b4eddb10d71a8d81cd6f11
2 files changed
+2
-2
.buildkite/test-pipeline.yaml
+1
-1
@@ -829,7 +829,7 @@ steps:
829
- pytest -v -s tests/kernels/quantization/test_flashinfer_scaled_mm.py
830
- pytest -v -s tests/kernels/quantization/test_flashinfer_nvfp4_scaled_mm.py
831
- pytest -v -s tests/kernels/moe/test_nvfp4_moe.py
832
- - pytest -v -s tests/kernels/moe/test_mxfp4_moe.py
832
+ - pytest -v -s tests/kernels/moe/test_ocp_mx_moe.py
833
# Fusion
834
- pytest -v -s tests/compile/test_fusion_all_reduce.py
835
- pytest -v -s tests/compile/test_fusion_attn.py::test_attention_quant_pattern
tests/quantization/test_quark.py
+1
-1
@@ -4,7 +4,7 @@
4
5
Run `pytest tests/quantization/test_quark.py`.
6
7
-See also `tests/kernels/moe/test_mxfp4_moe.py`.
7
+See also `tests/kernels/moe/test_ocp_mx_moe.py`.
8
"""
9
10
import importlib.metadata