[TEST] Speed up DS V2 accuracy test and turn up accuracy baseline (#3047)

### What this PR does / why we need it?
1. update expected accuracy for DeepSeek-V2-Lite
2. add batch size 

### Does this PR introduce _any_ user-facing change?
No

### How was this patch tested?
Accuracy CI passed

- vLLM version: v0.10.2
- vLLM main:
838d7116ba

Signed-off-by: hfadzxy <starmoon_zhang@163.com>
This commit is contained in:
zhangxinyuehfad
2025-09-20 00:40:33 +08:00
committed by GitHub
parent a22b532d38
commit e26fe1caf1

View File

@@ -3,11 +3,11 @@ tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.375
value: 0.385
- name: "exact_match,flexible-extract"
value: 0.375
value: 0.385
tensor_parallel_size: 2
batch_size: 8
batch_size: 32
gpu_memory_utilization: 0.7
apply_chat_template: False
fewshot_as_multiturn: False