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
[Docs] GSM8K Accuracy Evaluation doc update (#25360)
Signed-off-by: David Chen <530634352@qq.com>
WeiQing Chen committed
Sep 22, 2025 at 10:49 UTC
793be8d0579f11b3326f7e2099432c1433033571
1 file changed
+1
-1
tests/evals/gsm8k/README.md
+1
-1
@@ -19,7 +19,7 @@ pytest -s -v tests/gsm8k/test_gsm8k_correctness.py \
19
vllm serve Qwen/Qwen2.5-1.5B-Instruct --port 8000
20
21
# Run evaluation
22
-python tests/gsm8k/gsm8k_eval.py --port 8000
22
+python tests/evals/gsm8k/gsm8k_eval.py --port 8000
23
```
24
25
## Configuration Format