49e6983b3b
### What this PR does / why we need it?
Add accuracy test for qwen3-30b-a3b-w8a8
This PR depends on https://github.com/vllm-project/vllm-ascend/pull/3799
### How was this patch tested?
qwen3-30b-a3b-w8a8 accuarcy test ok:
https://github.com/vllm-project/vllm-ascend/actions/runs/19062045267/job/54443732877?pr=3807
- vLLM version: v0.11.0
- vLLM main:
83f478bb19
Signed-off-by: hfadzxy <starmoon_zhang@163.com>
17 lines
387 B
YAML
17 lines
387 B
YAML
model_name: "vllm-ascend/Qwen3-30B-A3B-W8A8"
|
|
hardware: "Atlas A2 Series"
|
|
tasks:
|
|
- name: "gsm8k"
|
|
metrics:
|
|
- name: "exact_match,strict-match"
|
|
value: 0.9
|
|
- name: "exact_match,flexible-extract"
|
|
value: 0.8
|
|
num_fewshot: 5
|
|
gpu_memory_utilization: 0.7
|
|
enable_expert_parallel: True
|
|
tensor_parallel_size: 2
|
|
apply_chat_template: False
|
|
fewshot_as_multiturn: False
|
|
quantization: ascend
|