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, 16:00 UTC
[TPU] Switch Test to Non-Sliding Window (#15981)
Signed-off-by: Robert Shaw <robshaw@redhat.com> Co-authored-by: Robert Shaw <robshaw@redhat.com>
Robert Shaw committed
Apr 3, 2025 at 14:28 UTC
f15e70d906aca5bb0e5ca7e4f1f857853ce5dd66
1 file changed
+1
-1
tests/tpu/test_compilation.py
+1
-1
@@ -30,7 +30,7 @@ def test_tpu_compilation():
30
n=N,
31
max_tokens=16)
32
33
- llm = LLM(model="Qwen/Qwen2.5-1.5B-Instruct",
33
+ llm = LLM(model="Qwen/Qwen2-1.5B-Instruct",
34
max_num_batched_tokens=256,
35
max_model_len=256,
36
max_num_seqs=32,