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, 23:45 UTC
[TPU][Test] Temporarily suspend this MoE model in test_basic.py. (#21560)
Signed-off-by: Qiliang Cui <derrhein@gmail.com>
QiliangCui committed
Jul 24, 2025 at 20:44 UTC
e0be2c4d0905d8ffd08f014421d21678a358b01b
1 file changed
+2
-1
tests/v1/tpu/test_basic.py
+2
-1
@@ -18,7 +18,8 @@ if TYPE_CHECKING:
18
19
MODELS = [
20
"Qwen/Qwen2.5-1.5B-Instruct",
21
- "Qwen/Qwen1.5-MoE-A2.7B",
21
+ # TODO: Enable this model when fixed.
22
+ # "Qwen/Qwen1.5-MoE-A2.7B",
23
# TODO: Enable this models with v6e
24
# "Qwen/Qwen2-7B-Instruct",
25
# "meta-llama/Llama-3.1-8B",