[Test] Add accuracy test for qwen3-30b-a3b-w8a8 (#3807)
### 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>
This commit is contained in:
2
.github/workflows/accuracy_test.yaml
vendored
2
.github/workflows/accuracy_test.yaml
vendored
@@ -68,6 +68,8 @@ jobs:
|
||||
model_name: Qwen2.5-Omni-7B
|
||||
- runner: a2-1
|
||||
model_name: Meta-Llama-3.1-8B-Instruct
|
||||
- runner: a2-4
|
||||
model_name: Qwen3-30B-A3B-W8A8
|
||||
fail-fast: false
|
||||
# test will be triggered when tag 'accuracy-test' & 'ready-for-test'
|
||||
if: >-
|
||||
|
||||
16
tests/e2e/models/configs/Qwen3-30B-A3B-W8A8.yaml
Normal file
16
tests/e2e/models/configs/Qwen3-30B-A3B-W8A8.yaml
Normal file
@@ -0,0 +1,16 @@
|
||||
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
|
||||
Reference in New Issue
Block a user