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 5, 18:30 UTC
[CI] fix LM Eval Qwen3.5 Models (B200) (#38632)
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Jiangyun Zhu committed
Mar 31, 2026 at 21:20 UTC
ea7bfde6e40d1c0bd2b03b2ace3ded561dff7026
1 file changed
+1
tests/evals/gsm8k/configs/Qwen3.5-397B-A17B-NVFP4-DEP2.yaml
+1
@@ -7,3 +7,4 @@ server_args: >-
7
--max-model-len 4096
8
--data-parallel-size 2
9
--enable-expert-parallel
10
+ --max-num-seqs 512