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 4, 22:30 UTC
[Bugfix][CI] Fix `tests/distributed/test_torchrun_example_moe.py` (#40349)
Signed-off-by: NickLucche <nlucches@redhat.com>
Nicolò Lucchesi committed
Apr 20, 2026 at 20:05 UTC
304d5ba1a04b6cbfa2b5bd377c2a89d350a10921
1 file changed
+2
tests/distributed/test_torchrun_example_moe.py
+2
@@ -38,6 +38,8 @@ llm = LLM(
38
distributed_executor_backend="external_launcher",
39
gpu_memory_utilization=random.uniform(0.7, 0.9),
40
seed=0,
41
+ max_model_len=1024,
42
+ max_num_seqs=16,
43
)
44
45
outputs = llm.generate(prompts, sampling_params)